test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    def test_pt_bart_classifier(test_device):
        compiler_cfg = _get_global_compiler_config()
        compiler_cfg.compile_depth = CompileDepth.SPLIT_GRAPH
    
        model_name = f"facebook/bart-large-mnli"
        model = download_model(BartForSequenceClassification.from_pretrained, model_name, torchscript=True)
        tokenizer = download_model(BartTokenizer.from_pretrained, model_name, pad_to_max_length=True)
        hypothesis = "Most of Mrinal Sen's work can be found in European collections."
        premise = "Calcutta seems to be the only other production center having any pretensions to artistic creativity at all, but ironically you're actually more likely to see the works of Satyajit Ray or Mrinal Sen shown in Europe or North America than in India itself."
    
        # generate inputs
        inputs_dict = tokenizer(
            premise,
            hypothesis,
            truncation=True,
            padding="max_length",
            max_length=256,
            truncation_strategy="only_first",
            return_tensors="pt",
        )
        decoder_input_ids = shift_tokens_right(
            inputs_dict["input_ids"], model.config.pad_token_id, model.config.decoder_start_token_id
        )
        inputs = [inputs_dict["input_ids"], inputs_dict["attention_mask"], decoder_input_ids]
    
        # Compile & feed data
        pt_mod = BartWrapper(model.model)
    
>       compiled_model = forge.compile(pt_mod, sample_inputs=inputs, module_name="pt_bart")

forge/test/models/pytorch/text/bart/test_bart.py:55: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

context = CompileContext(modules=[Module pt_bart], graph_name='pt_bart', compiler_cfg=CompilerConfig(enable_training=False, enab...in_recompile=False, recompile_count=0, target_cycles_offset=0, forge_module=None, compiled_binary=None, attach_to=None)

    def run_optimization_pass(context: CompileContext) -> CompileDepth:
        """
        Runs optimization passes.
    
        Parameters
        ----------
        context: CompileContext
            Compile context
    
        Returns
        -------
        CompileDepth - next compile stage
        """
        compiler_cfg = context.compiler_cfg
        graph_name = context.graph_name
        graph, intermediate_tensors = context.graph, context.intermediate_tensors
    
>       run_optimization_graph_passes(graph)
E       RuntimeError: TT_ASSERT @ /__w/tt-forge-fe/tt-forge-fe/forge/csrc/passes/commute_utils.cpp:1105: reshape->op_name() == "reshape"
E       info:
E       update_reshape_attr called for a non-reshape operation
E       backtrace:
E        --- tt::passes::update_reshape_attr(tt::graphlib::OpNode*, tt::graphlib::Shape)
E        --- tt::passes::commute_and_bypass(tt::graphlib::Graph*, std::vector<tt::graphlib::Node*, std::allocator<tt::graphlib::Node*> > const&)
E        --- tt::passes::erase_inverse_ops(tt::graphlib::Graph*)
E        --- tt::run_optimization_graph_passes(tt::graphlib::Graph*)
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xfc639) [0x7f4dca9c1639]
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xdf8f5) [0x7f4dca9a48f5]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x18b282) [0x555dce3f2282]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x5c7d) [0x555dce3e1f4d]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0x122) [0x555dce400882]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x818) [0x555dce3dcae8]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0xbb) [0x555dce40081b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]

forge/forge/compile.py:785: RuntimeError

test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    def test_bert_sequence_classification_pytorch(test_device):
        model, inputs, _ = generate_model_bert_seqcls_hf_pytorch(
            "textattack/bert-base-uncased-SST-2",
        )
    
        compiled_model = forge.compile(model, sample_inputs=inputs, module_name="pt_bert_sequence_classification")
    
>       co_out = compiled_model(*inputs)
E       TypeError: 'CompileResults' object is not callable

forge/test/models/pytorch/text/bert/test_bert.py:141: TypeError

variant = 'EleutherAI/gpt-neo-125M', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_gptneo_causal_lm(variant, test_device):
        # Set random seed for repeatability
        torch.manual_seed(42)
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load tokenizer and model
        # Variants: # EleutherAI/gpt-neo-125M, EleutherAI/gpt-neo-1.3B,
        # EleutherAI/gpt-neo-2.7B
    
        config = download_model(GPTNeoConfig.from_pretrained, variant)
        config_dict = config.to_dict()
        config_dict["return_dict"] = False
        config_dict["use_cache"] = False
        config = GPTNeoConfig(**config_dict)
    
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        tokenizer.pad_token = tokenizer.eos_token
        model = download_model(GPTNeoForCausalLM.from_pretrained, variant, config=config)
    
        # Sample input text
        prompt = "My name is Bert, and I am"
    
        inputs = tokenizer(prompt, return_tensors="pt", max_length=256, pad_to_max_length=True, truncation=True)
    
        # Wrapper to get around attention mask
        class Wrapper(torch.nn.Module):
            def __init__(self, model):
                super().__init__()
                self.model = model
    
            def forward(self, input_ids, attention_mask):
                return self.model(input_ids, None, attention_mask)
    
        inputs = [inputs["input_ids"], inputs["attention_mask"]]
>       compiled_model = forge.compile(
            Wrapper(model),
            sample_inputs=inputs,
            module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_")) + "_causal_lm",
        )

forge/test/models/pytorch/text/gptneo/test_gptneo.py:65: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
forge/forge/compile.py:634: in generate_initial_graph
    module, module_inputs = convert_to_forge_module(
forge/forge/compile.py:973: in convert_to_forge_module
    forge_module, dev_types, module_inputs = generate_forge_module(
forge/forge/tvm_to_python.py:2136: in generate_forge_module
    verify_framework_vs_forge_codegen(framework_outputs, forge_outputs, verify_cfg=verify_cfg)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

frame_outputs = [tensor([[[ -2.93149,  -3.04098,  -5.19186,  ..., -11.81308,  -8.60934,  -6.07345],
         [ -6.99371,  -5.94796, -1...],
         [-38.90412, -38.28091, -42.97676,  ..., -69.93178, -49.82716, -37.80742]]], grad_fn=<UnsafeViewBackward0>)]
forge_outputs = (Forge Tensor: tensor([[[ -2.93151,  -3.04100,  -5.19192,  ..., -11.81311,  -8.60940,  -6.07350],
         [ -6.99369,...2,  -5.60490,  -4.23273,  ..., -16.88002, -15.43275,  -9.50537]]], grad_fn=<UnsafeViewBackward0>), DataFormat.Float32,)
verify_cfg = DepricatedVerifyConfig(graph_name='graph', enabled=False, intermediates=False, rtol={torch.float32: None, torch.float1...ent_checking=True, enable_parameter_gradient_checking=True, _input_gradient_queue=None, _parameter_gradient_queue=None)

    def verify_framework_vs_forge_codegen(frame_outputs, forge_outputs, verify_cfg):
        from forge.verify.compare import compare_tensor_to_golden
    
        test_pass = True
        for i, (golden, output) in enumerate(zip(frame_outputs, forge_outputs)):
            test_pass &= compare_tensor_to_golden(
                f"Framework vs. Forge codegen output {i}", golden, output.value(), is_forge=False, verify_cfg=verify_cfg
            )
    
>           assert test_pass, f"Data mismatch on output {i} between framework and Forge codegen"
E           AssertionError: Data mismatch on output 0 between framework and Forge codegen

forge/forge/tvm_to_python.py:1985: AssertionError

variant = 'EleutherAI/gpt-neo-1.3B', test_device = None

    @pytest.mark.nightly
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_gptneo_sequence_classification(variant, test_device):
        # Load tokenizer and model from HuggingFace
        # Variants: # EleutherAI/gpt-neo-125M, EleutherAI/gpt-neo-1.3B,
        # EleutherAI/gpt-neo-2.7B
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        tokenizer.pad_token = tokenizer.eos_token
        model = download_model(GPTNeoForSequenceClassification.from_pretrained, variant, torchscript=True)
    
        # Load data sample
        review = "the movie was great!"
    
        # Data preprocessing
        input_tokens = tokenizer(
            review,
            max_length=32,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
    
        class Wrapper(torch.nn.Module):
            def __init__(self, model):
                super().__init__()
                self.model = model
    
            def forward(self, input_ids, attention_mask):
                return self.model(input_ids, None, attention_mask)
    
        inputs = [input_tokens["input_ids"], input_tokens["attention_mask"]]
    
>       compiled_model = forge.compile(
            Wrapper(model),
            sample_inputs=inputs,
            module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_")) + "_seq_cls",
        )

forge/test/models/pytorch/text/gptneo/test_gptneo.py:116: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
forge/forge/compile.py:634: in generate_initial_graph
    module, module_inputs = convert_to_forge_module(
forge/forge/compile.py:973: in convert_to_forge_module
    forge_module, dev_types, module_inputs = generate_forge_module(
forge/forge/tvm_to_python.py:2136: in generate_forge_module
    verify_framework_vs_forge_codegen(framework_outputs, forge_outputs, verify_cfg=verify_cfg)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

frame_outputs = [tensor([[ 2.02300, -1.06290]], grad_fn=<IndexBackward0>), tensor([[[[-8.65128e-02,  1.82043e-01,  2.00490e-01,  ..., ...51],
          [ 0.65266,  0.77656, -0.42172,  ..., -0.43564,  0.00645, -0.18691]]]], grad_fn=<PermuteBackward0>), ...]
forge_outputs = (Forge Tensor: tensor([[ 2.36522, -0.28600]], grad_fn=<IndexBackward0>), DataFormat.Float32, Forge Tensor: tensor([[[[...40,  0.44998, -0.12259,  ..., -0.48345,  0.07875, -0.03002]]]], grad_fn=<TransposeBackward0>), DataFormat.Float32, ...)
verify_cfg = DepricatedVerifyConfig(graph_name='graph', enabled=False, intermediates=False, rtol={torch.float32: None, torch.float1...ent_checking=True, enable_parameter_gradient_checking=True, _input_gradient_queue=None, _parameter_gradient_queue=None)

    def verify_framework_vs_forge_codegen(frame_outputs, forge_outputs, verify_cfg):
        from forge.verify.compare import compare_tensor_to_golden
    
        test_pass = True
        for i, (golden, output) in enumerate(zip(frame_outputs, forge_outputs)):
            test_pass &= compare_tensor_to_golden(
                f"Framework vs. Forge codegen output {i}", golden, output.value(), is_forge=False, verify_cfg=verify_cfg
            )
    
>           assert test_pass, f"Data mismatch on output {i} between framework and Forge codegen"
E           AssertionError: Data mismatch on output 3 between framework and Forge codegen

forge/forge/tvm_to_python.py:1985: AssertionError

variant = 'EleutherAI/gpt-neo-2.7B', test_device = None

    @pytest.mark.nightly
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_gptneo_sequence_classification(variant, test_device):
        # Load tokenizer and model from HuggingFace
        # Variants: # EleutherAI/gpt-neo-125M, EleutherAI/gpt-neo-1.3B,
        # EleutherAI/gpt-neo-2.7B
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        tokenizer.pad_token = tokenizer.eos_token
        model = download_model(GPTNeoForSequenceClassification.from_pretrained, variant, torchscript=True)
    
        # Load data sample
        review = "the movie was great!"
    
        # Data preprocessing
        input_tokens = tokenizer(
            review,
            max_length=32,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
    
        class Wrapper(torch.nn.Module):
            def __init__(self, model):
                super().__init__()
                self.model = model
    
            def forward(self, input_ids, attention_mask):
                return self.model(input_ids, None, attention_mask)
    
        inputs = [input_tokens["input_ids"], input_tokens["attention_mask"]]
    
>       compiled_model = forge.compile(
            Wrapper(model),
            sample_inputs=inputs,
            module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_")) + "_seq_cls",
        )

forge/test/models/pytorch/text/gptneo/test_gptneo.py:116: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
forge/forge/compile.py:634: in generate_initial_graph
    module, module_inputs = convert_to_forge_module(
forge/forge/compile.py:973: in convert_to_forge_module
    forge_module, dev_types, module_inputs = generate_forge_module(
forge/forge/tvm_to_python.py:2136: in generate_forge_module
    verify_framework_vs_forge_codegen(framework_outputs, forge_outputs, verify_cfg=verify_cfg)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

frame_outputs = [tensor([[-1.73945,  3.86908]], grad_fn=<IndexBackward0>), tensor([[[[-0.84780, -0.45597, -0.50286,  ...,  0.32681, -0...70],
          [-0.14309, -0.12644, -0.26851,  ...,  0.24723,  0.67294,  0.32695]]]], grad_fn=<PermuteBackward0>), ...]
forge_outputs = (Forge Tensor: tensor([[ 1.12671, -1.29598]], grad_fn=<IndexBackward0>), DataFormat.Float32, Forge Tensor: tensor([[[[....37702e-03,  ..., -3.20576e-01,  7.41636e-01, -2.53812e-01]]]], grad_fn=<TransposeBackward0>), DataFormat.Float32, ...)
verify_cfg = DepricatedVerifyConfig(graph_name='graph', enabled=False, intermediates=False, rtol={torch.float32: None, torch.float1...ent_checking=True, enable_parameter_gradient_checking=True, _input_gradient_queue=None, _parameter_gradient_queue=None)

    def verify_framework_vs_forge_codegen(frame_outputs, forge_outputs, verify_cfg):
        from forge.verify.compare import compare_tensor_to_golden
    
        test_pass = True
        for i, (golden, output) in enumerate(zip(frame_outputs, forge_outputs)):
            test_pass &= compare_tensor_to_golden(
                f"Framework vs. Forge codegen output {i}", golden, output.value(), is_forge=False, verify_cfg=verify_cfg
            )
    
>           assert test_pass, f"Data mismatch on output {i} between framework and Forge codegen"
E           AssertionError: Data mismatch on output 0 between framework and Forge codegen

forge/forge/tvm_to_python.py:1985: AssertionError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
filename = 'config.json', cache_dir = '/github/home/.cache/huggingface/hub'
force_download = False, resume_download = None, proxies = None, token = None
revision = None, local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
>           resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:403: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ('meta-llama/Meta-Llama-3-8B-Instruct', 'config.json')
kwargs = {'cache_dir': '/github/home/.cache/huggingface/hub', 'force_download': False, 'local_files_only': False, 'proxies': None, ...}
has_token = False, arg_name = 'local_files_only', arg_value = False

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

repo_id = 'meta-llama/Meta-Llama-3-8B-Instruct', filename = 'config.json'

    @validate_hf_hub_args
    def hf_hub_download(
        repo_id: str,
        filename: str,
        *,
        subfolder: Optional[str] = None,
        repo_type: Optional[str] = None,
        revision: Optional[str] = None,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        cache_dir: Union[str, Path, None] = None,
        local_dir: Union[str, Path, None] = None,
        user_agent: Union[Dict, str, None] = None,
        force_download: bool = False,
        proxies: Optional[Dict] = None,
        etag_timeout: float = constants.DEFAULT_ETAG_TIMEOUT,
        token: Union[bool, str, None] = None,
        local_files_only: bool = False,
        headers: Optional[Dict[str, str]] = None,
        endpoint: Optional[str] = None,
        resume_download: Optional[bool] = None,
        force_filename: Optional[str] = None,
        local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
    ) -> str:
        """Download a given file if it's not already present in the local cache.
    
        The new cache file layout looks like this:
        - The cache directory contains one subfolder per repo_id (namespaced by repo type)
        - inside each repo folder:
            - refs is a list of the latest known revision => commit_hash pairs
            - blobs contains the actual file blobs (identified by their git-sha or sha256, depending on
              whether they're LFS files or not)
            - snapshots contains one subfolder per commit, each "commit" contains the subset of the files
              that have been resolved at that particular commit. Each filename is a symlink to the blob
              at that particular commit.
    
        ```
        [  96]  .
        └── [ 160]  models--julien-c--EsperBERTo-small
            ├── [ 160]  blobs
            │   ├── [321M]  403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
            │   ├── [ 398]  7cb18dc9bafbfcf74629a4b760af1b160957a83e
            │   └── [1.4K]  d7edf6bd2a681fb0175f7735299831ee1b22b812
            ├── [  96]  refs
            │   └── [  40]  main
            └── [ 128]  snapshots
                ├── [ 128]  2439f60ef33a0d46d85da5001d52aeda5b00ce9f
                │   ├── [  52]  README.md -> ../../blobs/d7edf6bd2a681fb0175f7735299831ee1b22b812
                │   └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
                └── [ 128]  bbc77c8132af1cc5cf678da3f1ddf2de43606d48
                    ├── [  52]  README.md -> ../../blobs/7cb18dc9bafbfcf74629a4b760af1b160957a83e
                    └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
        ```
    
        If `local_dir` is provided, the file structure from the repo will be replicated in this location. When using this
        option, the `cache_dir` will not be used and a `.cache/huggingface/` folder will be created at the root of `local_dir`
        to store some metadata related to the downloaded files. While this mechanism is not as robust as the main
        cache-system, it's optimized for regularly pulling the latest version of a repository.
    
        Args:
            repo_id (`str`):
                A user or an organization name and a repo name separated by a `/`.
            filename (`str`):
                The name of the file in the repo.
            subfolder (`str`, *optional*):
                An optional value corresponding to a folder inside the model repo.
            repo_type (`str`, *optional*):
                Set to `"dataset"` or `"space"` if downloading from a dataset or space,
                `None` or `"model"` if downloading from a model. Default is `None`.
            revision (`str`, *optional*):
                An optional Git revision id which can be a branch name, a tag, or a
                commit hash.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            cache_dir (`str`, `Path`, *optional*):
                Path to the folder where cached files are stored.
            local_dir (`str` or `Path`, *optional*):
                If provided, the downloaded file will be placed under this directory.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether the file should be downloaded even if it already exists in
                the local cache.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            etag_timeout (`float`, *optional*, defaults to `10`):
                When fetching ETag, how many seconds to wait for the server to send
                data before giving up which is passed to `requests.request`.
            token (`str`, `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If a string, it's used as the authentication token.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, avoid downloading the file and return the path to the
                local cached file if it exists.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            `str`: Local path of file or if networking is off, last version of file cached on disk.
    
        Raises:
            [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it doesn't exist,
                or because it is set to `private` and you do not have access.
            [`~utils.RevisionNotFoundError`]
                If the revision to download from cannot be found.
            [`~utils.EntryNotFoundError`]
                If the file to download cannot be found.
            [`~utils.LocalEntryNotFoundError`]
                If network is disabled or unavailable and file is not found in cache.
            [`EnvironmentError`](https://docs.python.org/3/library/exceptions.html#EnvironmentError)
                If `token=True` but the token cannot be found.
            [`OSError`](https://docs.python.org/3/library/exceptions.html#OSError)
                If ETag cannot be determined.
            [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
                If some parameter value is invalid.
    
        """
        if constants.HF_HUB_ETAG_TIMEOUT != constants.DEFAULT_ETAG_TIMEOUT:
            # Respect environment variable above user value
            etag_timeout = constants.HF_HUB_ETAG_TIMEOUT
    
        if force_filename is not None:
            warnings.warn(
                "The `force_filename` parameter is deprecated as a new caching system, "
                "which keeps the filenames as they are on the Hub, is now in place.",
                FutureWarning,
            )
        if resume_download is not None:
            warnings.warn(
                "`resume_download` is deprecated and will be removed in version 1.0.0. "
                "Downloads always resume when possible. "
                "If you want to force a new download, use `force_download=True`.",
                FutureWarning,
            )
    
        if cache_dir is None:
            cache_dir = constants.HF_HUB_CACHE
        if revision is None:
            revision = constants.DEFAULT_REVISION
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
        if isinstance(local_dir, Path):
            local_dir = str(local_dir)
    
        if subfolder == "":
            subfolder = None
        if subfolder is not None:
            # This is used to create a URL, and not a local path, hence the forward slash.
            filename = f"{subfolder}/{filename}"
    
        if repo_type is None:
            repo_type = "model"
        if repo_type not in constants.REPO_TYPES:
            raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(constants.REPO_TYPES)}")
    
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
    
        if local_dir is not None:
            if local_dir_use_symlinks != "auto":
                warnings.warn(
                    "`local_dir_use_symlinks` parameter is deprecated and will be ignored. "
                    "The process to download files to a local folder has been updated and do "
                    "not rely on symlinks anymore. You only need to pass a destination folder "
                    "as`local_dir`.\n"
                    "For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder."
                )
    
            return _hf_hub_download_to_local_dir(
                # Destination
                local_dir=local_dir,
                # File info
                repo_id=repo_id,
                repo_type=repo_type,
                filename=filename,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                cache_dir=cache_dir,
                force_download=force_download,
                local_files_only=local_files_only,
            )
        else:
>           return _hf_hub_download_to_cache_dir(
                # Destination
                cache_dir=cache_dir,
                # File info
                repo_id=repo_id,
                filename=filename,
                repo_type=repo_type,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                local_files_only=local_files_only,
                force_download=force_download,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:860: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _hf_hub_download_to_cache_dir(
        *,
        # Destination
        cache_dir: str,
        # File info
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        # HTTP info
        endpoint: Optional[str],
        etag_timeout: float,
        headers: Dict[str, str],
        proxies: Optional[Dict],
        token: Optional[Union[bool, str]],
        # Additional options
        local_files_only: bool,
        force_download: bool,
    ) -> str:
        """Download a given file to a cache folder, if not already present.
    
        Method should not be called directly. Please use `hf_hub_download` instead.
        """
        locks_dir = os.path.join(cache_dir, ".locks")
        storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
    
        # cross platform transcription of filename, to be used as a local file path.
        relative_filename = os.path.join(*filename.split("/"))
        if os.name == "nt":
            if relative_filename.startswith("..\\") or "\\..\\" in relative_filename:
                raise ValueError(
                    f"Invalid filename: cannot handle filename '{relative_filename}' on Windows. Please ask the repository"
                    " owner to rename this file."
                )
    
        # if user provides a commit_hash and they already have the file on disk, shortcut everything.
        if REGEX_COMMIT_HASH.match(revision):
            pointer_path = _get_pointer_path(storage_folder, revision, relative_filename)
            if os.path.exists(pointer_path) and not force_download:
                return pointer_path
    
        # Try to get metadata (etag, commit_hash, url, size) from the server.
        # If we can't, a HEAD request error is returned.
        (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error(
            repo_id=repo_id,
            filename=filename,
            repo_type=repo_type,
            revision=revision,
            endpoint=endpoint,
            proxies=proxies,
            etag_timeout=etag_timeout,
            headers=headers,
            token=token,
            local_files_only=local_files_only,
            storage_folder=storage_folder,
            relative_filename=relative_filename,
        )
    
        # etag can be None for several reasons:
        # 1. we passed local_files_only.
        # 2. we don't have a connection
        # 3. Hub is down (HTTP 500, 503, 504)
        # 4. repo is not found -for example private or gated- and invalid/missing token sent
        # 5. Hub is blocked by a firewall or proxy is not set correctly.
        # => Try to get the last downloaded one from the specified revision.
        #
        # If the specified revision is a commit hash, look inside "snapshots".
        # If the specified revision is a branch or tag, look inside "refs".
        if head_call_error is not None:
            # Couldn't make a HEAD call => let's try to find a local file
            if not force_download:
                commit_hash = None
                if REGEX_COMMIT_HASH.match(revision):
                    commit_hash = revision
                else:
                    ref_path = os.path.join(storage_folder, "refs", revision)
                    if os.path.isfile(ref_path):
                        with open(ref_path) as f:
                            commit_hash = f.read()
    
                # Return pointer file if exists
                if commit_hash is not None:
                    pointer_path = _get_pointer_path(storage_folder, commit_hash, relative_filename)
                    if os.path.exists(pointer_path) and not force_download:
                        return pointer_path
    
            # Otherwise, raise appropriate error
>           _raise_on_head_call_error(head_call_error, force_download, local_files_only)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:967: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

head_call_error = GatedRepoError('401 Client Error. (Request ID: Root=1-67660e69-3621c16a3edfee2b1de55789;12d9f1d6-479f-4134-a90a-d7bc85.../Meta-Llama-3-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.')
force_download = False, local_files_only = False

    def _raise_on_head_call_error(head_call_error: Exception, force_download: bool, local_files_only: bool) -> NoReturn:
        """Raise an appropriate error when the HEAD call failed and we cannot locate a local file."""
    
        # No head call => we cannot force download.
        if force_download:
            if local_files_only:
                raise ValueError("Cannot pass 'force_download=True' and 'local_files_only=True' at the same time.")
            elif isinstance(head_call_error, OfflineModeIsEnabled):
                raise ValueError("Cannot pass 'force_download=True' when offline mode is enabled.") from head_call_error
            else:
                raise ValueError("Force download failed due to the above error.") from head_call_error
    
        # No head call + couldn't find an appropriate file on disk => raise an error.
        if local_files_only:
            raise LocalEntryNotFoundError(
                "Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable"
                " hf.co look-ups and downloads online, set 'local_files_only' to False."
            )
        elif isinstance(head_call_error, RepositoryNotFoundError) or isinstance(head_call_error, GatedRepoError):
            # Repo not found or gated => let's raise the actual error
>           raise head_call_error

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1482: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _get_metadata_or_catch_error(
        *,
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        endpoint: Optional[str],
        proxies: Optional[Dict],
        etag_timeout: Optional[float],
        headers: Dict[str, str],  # mutated inplace!
        token: Union[bool, str, None],
        local_files_only: bool,
        relative_filename: Optional[str] = None,  # only used to store `.no_exists` in cache
        storage_folder: Optional[str] = None,  # only used to store `.no_exists` in cache
    ) -> Union[
        # Either an exception is caught and returned
        Tuple[None, None, None, None, Exception],
        # Or the metadata is returned as
        # `(url_to_download, etag, commit_hash, expected_size, None)`
        Tuple[str, str, str, int, None],
    ]:
        """Get metadata for a file on the Hub, safely handling network issues.
    
        Returns either the etag, commit_hash and expected size of the file, or the error
        raised while fetching the metadata.
    
        NOTE: This function mutates `headers` inplace! It removes the `authorization` header
              if the file is a LFS blob and the domain of the url is different from the
              domain of the location (typically an S3 bucket).
        """
        if local_files_only:
            return (
                None,
                None,
                None,
                None,
                OfflineModeIsEnabled(
                    f"Cannot access file since 'local_files_only=True' as been set. (repo_id: {repo_id}, repo_type: {repo_type}, revision: {revision}, filename: {filename})"
                ),
            )
    
        url = hf_hub_url(repo_id, filename, repo_type=repo_type, revision=revision, endpoint=endpoint)
        url_to_download: str = url
        etag: Optional[str] = None
        commit_hash: Optional[str] = None
        expected_size: Optional[int] = None
        head_error_call: Optional[Exception] = None
    
        # Try to get metadata from the server.
        # Do not raise yet if the file is not found or not accessible.
        if not local_files_only:
            try:
                try:
>                   metadata = get_hf_file_metadata(
                        url=url, proxies=proxies, timeout=etag_timeout, headers=headers, token=token
                    )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1374: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ()
kwargs = {'headers': {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0;...3f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10, 'token': None, ...}
has_token = False, arg_name = 'token', arg_value = None

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

url = 'https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json'
token = None, proxies = None, timeout = 10, library_name = None
library_version = None, user_agent = None
headers = {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; transformers/4.47.0; session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}

    @validate_hf_hub_args
    def get_hf_file_metadata(
        url: str,
        token: Union[bool, str, None] = None,
        proxies: Optional[Dict] = None,
        timeout: Optional[float] = constants.DEFAULT_REQUEST_TIMEOUT,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        user_agent: Union[Dict, str, None] = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> HfFileMetadata:
        """Fetch metadata of a file versioned on the Hub for a given url.
    
        Args:
            url (`str`):
                File url, for example returned by [`hf_hub_url`].
            token (`str` or `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If `False` or `None`, no token is provided.
                    - If a string, it's used as the authentication token.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            timeout (`float`, *optional*, defaults to 10):
                How many seconds to wait for the server to send metadata before giving up.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            A [`HfFileMetadata`] object containing metadata such as location, etag, size and
            commit_hash.
        """
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
        hf_headers["Accept-Encoding"] = "identity"  # prevent any compression => we want to know the real size of the file
    
        # Retrieve metadata
>       r = _request_wrapper(
            method="HEAD",
            url=url,
            headers=hf_headers,
            allow_redirects=False,
            follow_relative_redirects=True,
            proxies=proxies,
            timeout=timeout,
        )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1294: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = True
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
>           response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:278: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = False
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}
response = <Response [401]>

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
            response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )
    
            # If redirection, we redirect only relative paths.
            # This is useful in case of a renamed repository.
            if 300 <= response.status_code <= 399:
                parsed_target = urlparse(response.headers["Location"])
                if parsed_target.netloc == "":
                    # This means it is a relative 'location' headers, as allowed by RFC 7231.
                    # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
                    # We want to follow this relative redirect !
                    #
                    # Highly inspired by `resolve_redirects` from requests library.
                    # See https://github.com/psf/requests/blob/main/requests/sessions.py#L159
                    next_url = urlparse(url)._replace(path=parsed_target.path).geturl()
                    return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params)
            return response
    
        # Perform request and return if status_code is not in the retry list.
        response = get_session().request(method=method, url=url, **params)
>       hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:302: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e69-3621c16a3edfee2b1de55789;12d9f1d6-479f-4134-a90a-d7bc8531b0ea)
E               
E               Cannot access gated repo for url https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json.
E               Access to model meta-llama/Meta-Llama-3-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'meta-llama/Meta-Llama-3-8B-Instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_llama3_causal_lm(variant, test_device):
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load model (with tokenizer)
>       tokenizer = download_model(AutoTokenizer.from_pretrained, variant)

forge/test/models/pytorch/text/llama/test_llama3.py:128: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/test/utils.py:15: in download_model
    return download_func(*args, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:878: in from_pretrained
    config = AutoConfig.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1021: in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:590: in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:649: in _get_config_dict
    resolved_config_file = cached_file(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
filename = 'config.json', cache_dir = '/github/home/.cache/huggingface/hub'
force_download = False, resume_download = None, proxies = None, token = None
revision = None, local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
            resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )
        except GatedRepoError as e:
            resolved_file = _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)
            if resolved_file is not None or not _raise_exceptions_for_gated_repo:
                return resolved_file
>           raise EnvironmentError(
                "You are trying to access a gated repo.\nMake sure to have access to it at "
                f"https://huggingface.co/{path_or_repo_id}.\n{str(e)}"
            ) from e
E           OSError: You are trying to access a gated repo.
E           Make sure to have access to it at https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct.
E           401 Client Error. (Request ID: Root=1-67660e69-3621c16a3edfee2b1de55789;12d9f1d6-479f-4134-a90a-d7bc8531b0ea)
E           
E           Cannot access gated repo for url https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json.
E           Access to model meta-llama/Meta-Llama-3-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:421: OSError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo_id = 'meta-llama/Llama-3.1-8B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
>           resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:403: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ('meta-llama/Llama-3.1-8B-Instruct', 'config.json')
kwargs = {'cache_dir': '/github/home/.cache/huggingface/hub', 'force_download': False, 'local_files_only': False, 'proxies': None, ...}
has_token = False, arg_name = 'local_files_only', arg_value = False

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

repo_id = 'meta-llama/Llama-3.1-8B-Instruct', filename = 'config.json'

    @validate_hf_hub_args
    def hf_hub_download(
        repo_id: str,
        filename: str,
        *,
        subfolder: Optional[str] = None,
        repo_type: Optional[str] = None,
        revision: Optional[str] = None,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        cache_dir: Union[str, Path, None] = None,
        local_dir: Union[str, Path, None] = None,
        user_agent: Union[Dict, str, None] = None,
        force_download: bool = False,
        proxies: Optional[Dict] = None,
        etag_timeout: float = constants.DEFAULT_ETAG_TIMEOUT,
        token: Union[bool, str, None] = None,
        local_files_only: bool = False,
        headers: Optional[Dict[str, str]] = None,
        endpoint: Optional[str] = None,
        resume_download: Optional[bool] = None,
        force_filename: Optional[str] = None,
        local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
    ) -> str:
        """Download a given file if it's not already present in the local cache.
    
        The new cache file layout looks like this:
        - The cache directory contains one subfolder per repo_id (namespaced by repo type)
        - inside each repo folder:
            - refs is a list of the latest known revision => commit_hash pairs
            - blobs contains the actual file blobs (identified by their git-sha or sha256, depending on
              whether they're LFS files or not)
            - snapshots contains one subfolder per commit, each "commit" contains the subset of the files
              that have been resolved at that particular commit. Each filename is a symlink to the blob
              at that particular commit.
    
        ```
        [  96]  .
        └── [ 160]  models--julien-c--EsperBERTo-small
            ├── [ 160]  blobs
            │   ├── [321M]  403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
            │   ├── [ 398]  7cb18dc9bafbfcf74629a4b760af1b160957a83e
            │   └── [1.4K]  d7edf6bd2a681fb0175f7735299831ee1b22b812
            ├── [  96]  refs
            │   └── [  40]  main
            └── [ 128]  snapshots
                ├── [ 128]  2439f60ef33a0d46d85da5001d52aeda5b00ce9f
                │   ├── [  52]  README.md -> ../../blobs/d7edf6bd2a681fb0175f7735299831ee1b22b812
                │   └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
                └── [ 128]  bbc77c8132af1cc5cf678da3f1ddf2de43606d48
                    ├── [  52]  README.md -> ../../blobs/7cb18dc9bafbfcf74629a4b760af1b160957a83e
                    └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
        ```
    
        If `local_dir` is provided, the file structure from the repo will be replicated in this location. When using this
        option, the `cache_dir` will not be used and a `.cache/huggingface/` folder will be created at the root of `local_dir`
        to store some metadata related to the downloaded files. While this mechanism is not as robust as the main
        cache-system, it's optimized for regularly pulling the latest version of a repository.
    
        Args:
            repo_id (`str`):
                A user or an organization name and a repo name separated by a `/`.
            filename (`str`):
                The name of the file in the repo.
            subfolder (`str`, *optional*):
                An optional value corresponding to a folder inside the model repo.
            repo_type (`str`, *optional*):
                Set to `"dataset"` or `"space"` if downloading from a dataset or space,
                `None` or `"model"` if downloading from a model. Default is `None`.
            revision (`str`, *optional*):
                An optional Git revision id which can be a branch name, a tag, or a
                commit hash.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            cache_dir (`str`, `Path`, *optional*):
                Path to the folder where cached files are stored.
            local_dir (`str` or `Path`, *optional*):
                If provided, the downloaded file will be placed under this directory.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether the file should be downloaded even if it already exists in
                the local cache.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            etag_timeout (`float`, *optional*, defaults to `10`):
                When fetching ETag, how many seconds to wait for the server to send
                data before giving up which is passed to `requests.request`.
            token (`str`, `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If a string, it's used as the authentication token.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, avoid downloading the file and return the path to the
                local cached file if it exists.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            `str`: Local path of file or if networking is off, last version of file cached on disk.
    
        Raises:
            [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it doesn't exist,
                or because it is set to `private` and you do not have access.
            [`~utils.RevisionNotFoundError`]
                If the revision to download from cannot be found.
            [`~utils.EntryNotFoundError`]
                If the file to download cannot be found.
            [`~utils.LocalEntryNotFoundError`]
                If network is disabled or unavailable and file is not found in cache.
            [`EnvironmentError`](https://docs.python.org/3/library/exceptions.html#EnvironmentError)
                If `token=True` but the token cannot be found.
            [`OSError`](https://docs.python.org/3/library/exceptions.html#OSError)
                If ETag cannot be determined.
            [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
                If some parameter value is invalid.
    
        """
        if constants.HF_HUB_ETAG_TIMEOUT != constants.DEFAULT_ETAG_TIMEOUT:
            # Respect environment variable above user value
            etag_timeout = constants.HF_HUB_ETAG_TIMEOUT
    
        if force_filename is not None:
            warnings.warn(
                "The `force_filename` parameter is deprecated as a new caching system, "
                "which keeps the filenames as they are on the Hub, is now in place.",
                FutureWarning,
            )
        if resume_download is not None:
            warnings.warn(
                "`resume_download` is deprecated and will be removed in version 1.0.0. "
                "Downloads always resume when possible. "
                "If you want to force a new download, use `force_download=True`.",
                FutureWarning,
            )
    
        if cache_dir is None:
            cache_dir = constants.HF_HUB_CACHE
        if revision is None:
            revision = constants.DEFAULT_REVISION
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
        if isinstance(local_dir, Path):
            local_dir = str(local_dir)
    
        if subfolder == "":
            subfolder = None
        if subfolder is not None:
            # This is used to create a URL, and not a local path, hence the forward slash.
            filename = f"{subfolder}/{filename}"
    
        if repo_type is None:
            repo_type = "model"
        if repo_type not in constants.REPO_TYPES:
            raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(constants.REPO_TYPES)}")
    
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
    
        if local_dir is not None:
            if local_dir_use_symlinks != "auto":
                warnings.warn(
                    "`local_dir_use_symlinks` parameter is deprecated and will be ignored. "
                    "The process to download files to a local folder has been updated and do "
                    "not rely on symlinks anymore. You only need to pass a destination folder "
                    "as`local_dir`.\n"
                    "For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder."
                )
    
            return _hf_hub_download_to_local_dir(
                # Destination
                local_dir=local_dir,
                # File info
                repo_id=repo_id,
                repo_type=repo_type,
                filename=filename,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                cache_dir=cache_dir,
                force_download=force_download,
                local_files_only=local_files_only,
            )
        else:
>           return _hf_hub_download_to_cache_dir(
                # Destination
                cache_dir=cache_dir,
                # File info
                repo_id=repo_id,
                filename=filename,
                repo_type=repo_type,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                local_files_only=local_files_only,
                force_download=force_download,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:860: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _hf_hub_download_to_cache_dir(
        *,
        # Destination
        cache_dir: str,
        # File info
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        # HTTP info
        endpoint: Optional[str],
        etag_timeout: float,
        headers: Dict[str, str],
        proxies: Optional[Dict],
        token: Optional[Union[bool, str]],
        # Additional options
        local_files_only: bool,
        force_download: bool,
    ) -> str:
        """Download a given file to a cache folder, if not already present.
    
        Method should not be called directly. Please use `hf_hub_download` instead.
        """
        locks_dir = os.path.join(cache_dir, ".locks")
        storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
    
        # cross platform transcription of filename, to be used as a local file path.
        relative_filename = os.path.join(*filename.split("/"))
        if os.name == "nt":
            if relative_filename.startswith("..\\") or "\\..\\" in relative_filename:
                raise ValueError(
                    f"Invalid filename: cannot handle filename '{relative_filename}' on Windows. Please ask the repository"
                    " owner to rename this file."
                )
    
        # if user provides a commit_hash and they already have the file on disk, shortcut everything.
        if REGEX_COMMIT_HASH.match(revision):
            pointer_path = _get_pointer_path(storage_folder, revision, relative_filename)
            if os.path.exists(pointer_path) and not force_download:
                return pointer_path
    
        # Try to get metadata (etag, commit_hash, url, size) from the server.
        # If we can't, a HEAD request error is returned.
        (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error(
            repo_id=repo_id,
            filename=filename,
            repo_type=repo_type,
            revision=revision,
            endpoint=endpoint,
            proxies=proxies,
            etag_timeout=etag_timeout,
            headers=headers,
            token=token,
            local_files_only=local_files_only,
            storage_folder=storage_folder,
            relative_filename=relative_filename,
        )
    
        # etag can be None for several reasons:
        # 1. we passed local_files_only.
        # 2. we don't have a connection
        # 3. Hub is down (HTTP 500, 503, 504)
        # 4. repo is not found -for example private or gated- and invalid/missing token sent
        # 5. Hub is blocked by a firewall or proxy is not set correctly.
        # => Try to get the last downloaded one from the specified revision.
        #
        # If the specified revision is a commit hash, look inside "snapshots".
        # If the specified revision is a branch or tag, look inside "refs".
        if head_call_error is not None:
            # Couldn't make a HEAD call => let's try to find a local file
            if not force_download:
                commit_hash = None
                if REGEX_COMMIT_HASH.match(revision):
                    commit_hash = revision
                else:
                    ref_path = os.path.join(storage_folder, "refs", revision)
                    if os.path.isfile(ref_path):
                        with open(ref_path) as f:
                            commit_hash = f.read()
    
                # Return pointer file if exists
                if commit_hash is not None:
                    pointer_path = _get_pointer_path(storage_folder, commit_hash, relative_filename)
                    if os.path.exists(pointer_path) and not force_download:
                        return pointer_path
    
            # Otherwise, raise appropriate error
>           _raise_on_head_call_error(head_call_error, force_download, local_files_only)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:967: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

head_call_error = GatedRepoError('401 Client Error. (Request ID: Root=1-67660e69-7acfb2bc4c45ab9a1cfb3fe0;ebed6745-26e2-4cfb-bf5f-42b6fb...ama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.')
force_download = False, local_files_only = False

    def _raise_on_head_call_error(head_call_error: Exception, force_download: bool, local_files_only: bool) -> NoReturn:
        """Raise an appropriate error when the HEAD call failed and we cannot locate a local file."""
    
        # No head call => we cannot force download.
        if force_download:
            if local_files_only:
                raise ValueError("Cannot pass 'force_download=True' and 'local_files_only=True' at the same time.")
            elif isinstance(head_call_error, OfflineModeIsEnabled):
                raise ValueError("Cannot pass 'force_download=True' when offline mode is enabled.") from head_call_error
            else:
                raise ValueError("Force download failed due to the above error.") from head_call_error
    
        # No head call + couldn't find an appropriate file on disk => raise an error.
        if local_files_only:
            raise LocalEntryNotFoundError(
                "Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable"
                " hf.co look-ups and downloads online, set 'local_files_only' to False."
            )
        elif isinstance(head_call_error, RepositoryNotFoundError) or isinstance(head_call_error, GatedRepoError):
            # Repo not found or gated => let's raise the actual error
>           raise head_call_error

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1482: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _get_metadata_or_catch_error(
        *,
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        endpoint: Optional[str],
        proxies: Optional[Dict],
        etag_timeout: Optional[float],
        headers: Dict[str, str],  # mutated inplace!
        token: Union[bool, str, None],
        local_files_only: bool,
        relative_filename: Optional[str] = None,  # only used to store `.no_exists` in cache
        storage_folder: Optional[str] = None,  # only used to store `.no_exists` in cache
    ) -> Union[
        # Either an exception is caught and returned
        Tuple[None, None, None, None, Exception],
        # Or the metadata is returned as
        # `(url_to_download, etag, commit_hash, expected_size, None)`
        Tuple[str, str, str, int, None],
    ]:
        """Get metadata for a file on the Hub, safely handling network issues.
    
        Returns either the etag, commit_hash and expected size of the file, or the error
        raised while fetching the metadata.
    
        NOTE: This function mutates `headers` inplace! It removes the `authorization` header
              if the file is a LFS blob and the domain of the url is different from the
              domain of the location (typically an S3 bucket).
        """
        if local_files_only:
            return (
                None,
                None,
                None,
                None,
                OfflineModeIsEnabled(
                    f"Cannot access file since 'local_files_only=True' as been set. (repo_id: {repo_id}, repo_type: {repo_type}, revision: {revision}, filename: {filename})"
                ),
            )
    
        url = hf_hub_url(repo_id, filename, repo_type=repo_type, revision=revision, endpoint=endpoint)
        url_to_download: str = url
        etag: Optional[str] = None
        commit_hash: Optional[str] = None
        expected_size: Optional[int] = None
        head_error_call: Optional[Exception] = None
    
        # Try to get metadata from the server.
        # Do not raise yet if the file is not found or not accessible.
        if not local_files_only:
            try:
                try:
>                   metadata = get_hf_file_metadata(
                        url=url, proxies=proxies, timeout=etag_timeout, headers=headers, token=token
                    )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1374: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ()
kwargs = {'headers': {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0;...3f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10, 'token': None, ...}
has_token = False, arg_name = 'token', arg_value = None

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

url = 'https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json'
token = None, proxies = None, timeout = 10, library_name = None
library_version = None, user_agent = None
headers = {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; transformers/4.47.0; session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}

    @validate_hf_hub_args
    def get_hf_file_metadata(
        url: str,
        token: Union[bool, str, None] = None,
        proxies: Optional[Dict] = None,
        timeout: Optional[float] = constants.DEFAULT_REQUEST_TIMEOUT,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        user_agent: Union[Dict, str, None] = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> HfFileMetadata:
        """Fetch metadata of a file versioned on the Hub for a given url.
    
        Args:
            url (`str`):
                File url, for example returned by [`hf_hub_url`].
            token (`str` or `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If `False` or `None`, no token is provided.
                    - If a string, it's used as the authentication token.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            timeout (`float`, *optional*, defaults to 10):
                How many seconds to wait for the server to send metadata before giving up.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            A [`HfFileMetadata`] object containing metadata such as location, etag, size and
            commit_hash.
        """
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
        hf_headers["Accept-Encoding"] = "identity"  # prevent any compression => we want to know the real size of the file
    
        # Retrieve metadata
>       r = _request_wrapper(
            method="HEAD",
            url=url,
            headers=hf_headers,
            allow_redirects=False,
            follow_relative_redirects=True,
            proxies=proxies,
            timeout=timeout,
        )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1294: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = True
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
>           response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:278: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = False
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}
response = <Response [401]>

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
            response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )
    
            # If redirection, we redirect only relative paths.
            # This is useful in case of a renamed repository.
            if 300 <= response.status_code <= 399:
                parsed_target = urlparse(response.headers["Location"])
                if parsed_target.netloc == "":
                    # This means it is a relative 'location' headers, as allowed by RFC 7231.
                    # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
                    # We want to follow this relative redirect !
                    #
                    # Highly inspired by `resolve_redirects` from requests library.
                    # See https://github.com/psf/requests/blob/main/requests/sessions.py#L159
                    next_url = urlparse(url)._replace(path=parsed_target.path).geturl()
                    return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params)
            return response
    
        # Perform request and return if status_code is not in the retry list.
        response = get_session().request(method=method, url=url, **params)
>       hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:302: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e69-7acfb2bc4c45ab9a1cfb3fe0;ebed6745-26e2-4cfb-bf5f-42b6fb9de8cf)
E               
E               Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json.
E               Access to model meta-llama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'meta-llama/Llama-3.1-8B-Instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_llama3_causal_lm(variant, test_device):
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load model (with tokenizer)
>       tokenizer = download_model(AutoTokenizer.from_pretrained, variant)

forge/test/models/pytorch/text/llama/test_llama3.py:128: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/test/utils.py:15: in download_model
    return download_func(*args, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:878: in from_pretrained
    config = AutoConfig.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1021: in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:590: in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:649: in _get_config_dict
    resolved_config_file = cached_file(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo_id = 'meta-llama/Llama-3.1-8B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
            resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )
        except GatedRepoError as e:
            resolved_file = _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)
            if resolved_file is not None or not _raise_exceptions_for_gated_repo:
                return resolved_file
>           raise EnvironmentError(
                "You are trying to access a gated repo.\nMake sure to have access to it at "
                f"https://huggingface.co/{path_or_repo_id}.\n{str(e)}"
            ) from e
E           OSError: You are trying to access a gated repo.
E           Make sure to have access to it at https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct.
E           401 Client Error. (Request ID: Root=1-67660e69-7acfb2bc4c45ab9a1cfb3fe0;ebed6745-26e2-4cfb-bf5f-42b6fb9de8cf)
E           
E           Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json.
E           Access to model meta-llama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:421: OSError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo_id = 'meta-llama/Llama-3.2-1B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
>           resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:403: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ('meta-llama/Llama-3.2-1B-Instruct', 'config.json')
kwargs = {'cache_dir': '/github/home/.cache/huggingface/hub', 'force_download': False, 'local_files_only': False, 'proxies': None, ...}
has_token = False, arg_name = 'local_files_only', arg_value = False

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

repo_id = 'meta-llama/Llama-3.2-1B-Instruct', filename = 'config.json'

    @validate_hf_hub_args
    def hf_hub_download(
        repo_id: str,
        filename: str,
        *,
        subfolder: Optional[str] = None,
        repo_type: Optional[str] = None,
        revision: Optional[str] = None,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        cache_dir: Union[str, Path, None] = None,
        local_dir: Union[str, Path, None] = None,
        user_agent: Union[Dict, str, None] = None,
        force_download: bool = False,
        proxies: Optional[Dict] = None,
        etag_timeout: float = constants.DEFAULT_ETAG_TIMEOUT,
        token: Union[bool, str, None] = None,
        local_files_only: bool = False,
        headers: Optional[Dict[str, str]] = None,
        endpoint: Optional[str] = None,
        resume_download: Optional[bool] = None,
        force_filename: Optional[str] = None,
        local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
    ) -> str:
        """Download a given file if it's not already present in the local cache.
    
        The new cache file layout looks like this:
        - The cache directory contains one subfolder per repo_id (namespaced by repo type)
        - inside each repo folder:
            - refs is a list of the latest known revision => commit_hash pairs
            - blobs contains the actual file blobs (identified by their git-sha or sha256, depending on
              whether they're LFS files or not)
            - snapshots contains one subfolder per commit, each "commit" contains the subset of the files
              that have been resolved at that particular commit. Each filename is a symlink to the blob
              at that particular commit.
    
        ```
        [  96]  .
        └── [ 160]  models--julien-c--EsperBERTo-small
            ├── [ 160]  blobs
            │   ├── [321M]  403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
            │   ├── [ 398]  7cb18dc9bafbfcf74629a4b760af1b160957a83e
            │   └── [1.4K]  d7edf6bd2a681fb0175f7735299831ee1b22b812
            ├── [  96]  refs
            │   └── [  40]  main
            └── [ 128]  snapshots
                ├── [ 128]  2439f60ef33a0d46d85da5001d52aeda5b00ce9f
                │   ├── [  52]  README.md -> ../../blobs/d7edf6bd2a681fb0175f7735299831ee1b22b812
                │   └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
                └── [ 128]  bbc77c8132af1cc5cf678da3f1ddf2de43606d48
                    ├── [  52]  README.md -> ../../blobs/7cb18dc9bafbfcf74629a4b760af1b160957a83e
                    └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
        ```
    
        If `local_dir` is provided, the file structure from the repo will be replicated in this location. When using this
        option, the `cache_dir` will not be used and a `.cache/huggingface/` folder will be created at the root of `local_dir`
        to store some metadata related to the downloaded files. While this mechanism is not as robust as the main
        cache-system, it's optimized for regularly pulling the latest version of a repository.
    
        Args:
            repo_id (`str`):
                A user or an organization name and a repo name separated by a `/`.
            filename (`str`):
                The name of the file in the repo.
            subfolder (`str`, *optional*):
                An optional value corresponding to a folder inside the model repo.
            repo_type (`str`, *optional*):
                Set to `"dataset"` or `"space"` if downloading from a dataset or space,
                `None` or `"model"` if downloading from a model. Default is `None`.
            revision (`str`, *optional*):
                An optional Git revision id which can be a branch name, a tag, or a
                commit hash.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            cache_dir (`str`, `Path`, *optional*):
                Path to the folder where cached files are stored.
            local_dir (`str` or `Path`, *optional*):
                If provided, the downloaded file will be placed under this directory.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether the file should be downloaded even if it already exists in
                the local cache.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            etag_timeout (`float`, *optional*, defaults to `10`):
                When fetching ETag, how many seconds to wait for the server to send
                data before giving up which is passed to `requests.request`.
            token (`str`, `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If a string, it's used as the authentication token.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, avoid downloading the file and return the path to the
                local cached file if it exists.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            `str`: Local path of file or if networking is off, last version of file cached on disk.
    
        Raises:
            [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it doesn't exist,
                or because it is set to `private` and you do not have access.
            [`~utils.RevisionNotFoundError`]
                If the revision to download from cannot be found.
            [`~utils.EntryNotFoundError`]
                If the file to download cannot be found.
            [`~utils.LocalEntryNotFoundError`]
                If network is disabled or unavailable and file is not found in cache.
            [`EnvironmentError`](https://docs.python.org/3/library/exceptions.html#EnvironmentError)
                If `token=True` but the token cannot be found.
            [`OSError`](https://docs.python.org/3/library/exceptions.html#OSError)
                If ETag cannot be determined.
            [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
                If some parameter value is invalid.
    
        """
        if constants.HF_HUB_ETAG_TIMEOUT != constants.DEFAULT_ETAG_TIMEOUT:
            # Respect environment variable above user value
            etag_timeout = constants.HF_HUB_ETAG_TIMEOUT
    
        if force_filename is not None:
            warnings.warn(
                "The `force_filename` parameter is deprecated as a new caching system, "
                "which keeps the filenames as they are on the Hub, is now in place.",
                FutureWarning,
            )
        if resume_download is not None:
            warnings.warn(
                "`resume_download` is deprecated and will be removed in version 1.0.0. "
                "Downloads always resume when possible. "
                "If you want to force a new download, use `force_download=True`.",
                FutureWarning,
            )
    
        if cache_dir is None:
            cache_dir = constants.HF_HUB_CACHE
        if revision is None:
            revision = constants.DEFAULT_REVISION
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
        if isinstance(local_dir, Path):
            local_dir = str(local_dir)
    
        if subfolder == "":
            subfolder = None
        if subfolder is not None:
            # This is used to create a URL, and not a local path, hence the forward slash.
            filename = f"{subfolder}/{filename}"
    
        if repo_type is None:
            repo_type = "model"
        if repo_type not in constants.REPO_TYPES:
            raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(constants.REPO_TYPES)}")
    
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
    
        if local_dir is not None:
            if local_dir_use_symlinks != "auto":
                warnings.warn(
                    "`local_dir_use_symlinks` parameter is deprecated and will be ignored. "
                    "The process to download files to a local folder has been updated and do "
                    "not rely on symlinks anymore. You only need to pass a destination folder "
                    "as`local_dir`.\n"
                    "For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder."
                )
    
            return _hf_hub_download_to_local_dir(
                # Destination
                local_dir=local_dir,
                # File info
                repo_id=repo_id,
                repo_type=repo_type,
                filename=filename,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                cache_dir=cache_dir,
                force_download=force_download,
                local_files_only=local_files_only,
            )
        else:
>           return _hf_hub_download_to_cache_dir(
                # Destination
                cache_dir=cache_dir,
                # File info
                repo_id=repo_id,
                filename=filename,
                repo_type=repo_type,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                local_files_only=local_files_only,
                force_download=force_download,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:860: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _hf_hub_download_to_cache_dir(
        *,
        # Destination
        cache_dir: str,
        # File info
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        # HTTP info
        endpoint: Optional[str],
        etag_timeout: float,
        headers: Dict[str, str],
        proxies: Optional[Dict],
        token: Optional[Union[bool, str]],
        # Additional options
        local_files_only: bool,
        force_download: bool,
    ) -> str:
        """Download a given file to a cache folder, if not already present.
    
        Method should not be called directly. Please use `hf_hub_download` instead.
        """
        locks_dir = os.path.join(cache_dir, ".locks")
        storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
    
        # cross platform transcription of filename, to be used as a local file path.
        relative_filename = os.path.join(*filename.split("/"))
        if os.name == "nt":
            if relative_filename.startswith("..\\") or "\\..\\" in relative_filename:
                raise ValueError(
                    f"Invalid filename: cannot handle filename '{relative_filename}' on Windows. Please ask the repository"
                    " owner to rename this file."
                )
    
        # if user provides a commit_hash and they already have the file on disk, shortcut everything.
        if REGEX_COMMIT_HASH.match(revision):
            pointer_path = _get_pointer_path(storage_folder, revision, relative_filename)
            if os.path.exists(pointer_path) and not force_download:
                return pointer_path
    
        # Try to get metadata (etag, commit_hash, url, size) from the server.
        # If we can't, a HEAD request error is returned.
        (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error(
            repo_id=repo_id,
            filename=filename,
            repo_type=repo_type,
            revision=revision,
            endpoint=endpoint,
            proxies=proxies,
            etag_timeout=etag_timeout,
            headers=headers,
            token=token,
            local_files_only=local_files_only,
            storage_folder=storage_folder,
            relative_filename=relative_filename,
        )
    
        # etag can be None for several reasons:
        # 1. we passed local_files_only.
        # 2. we don't have a connection
        # 3. Hub is down (HTTP 500, 503, 504)
        # 4. repo is not found -for example private or gated- and invalid/missing token sent
        # 5. Hub is blocked by a firewall or proxy is not set correctly.
        # => Try to get the last downloaded one from the specified revision.
        #
        # If the specified revision is a commit hash, look inside "snapshots".
        # If the specified revision is a branch or tag, look inside "refs".
        if head_call_error is not None:
            # Couldn't make a HEAD call => let's try to find a local file
            if not force_download:
                commit_hash = None
                if REGEX_COMMIT_HASH.match(revision):
                    commit_hash = revision
                else:
                    ref_path = os.path.join(storage_folder, "refs", revision)
                    if os.path.isfile(ref_path):
                        with open(ref_path) as f:
                            commit_hash = f.read()
    
                # Return pointer file if exists
                if commit_hash is not None:
                    pointer_path = _get_pointer_path(storage_folder, commit_hash, relative_filename)
                    if os.path.exists(pointer_path) and not force_download:
                        return pointer_path
    
            # Otherwise, raise appropriate error
>           _raise_on_head_call_error(head_call_error, force_download, local_files_only)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:967: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

head_call_error = GatedRepoError('401 Client Error. (Request ID: Root=1-67660e69-686765224a9df84c50313d6e;190c776d-d322-4bc8-9f1b-be5aa3...ama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.')
force_download = False, local_files_only = False

    def _raise_on_head_call_error(head_call_error: Exception, force_download: bool, local_files_only: bool) -> NoReturn:
        """Raise an appropriate error when the HEAD call failed and we cannot locate a local file."""
    
        # No head call => we cannot force download.
        if force_download:
            if local_files_only:
                raise ValueError("Cannot pass 'force_download=True' and 'local_files_only=True' at the same time.")
            elif isinstance(head_call_error, OfflineModeIsEnabled):
                raise ValueError("Cannot pass 'force_download=True' when offline mode is enabled.") from head_call_error
            else:
                raise ValueError("Force download failed due to the above error.") from head_call_error
    
        # No head call + couldn't find an appropriate file on disk => raise an error.
        if local_files_only:
            raise LocalEntryNotFoundError(
                "Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable"
                " hf.co look-ups and downloads online, set 'local_files_only' to False."
            )
        elif isinstance(head_call_error, RepositoryNotFoundError) or isinstance(head_call_error, GatedRepoError):
            # Repo not found or gated => let's raise the actual error
>           raise head_call_error

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1482: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _get_metadata_or_catch_error(
        *,
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        endpoint: Optional[str],
        proxies: Optional[Dict],
        etag_timeout: Optional[float],
        headers: Dict[str, str],  # mutated inplace!
        token: Union[bool, str, None],
        local_files_only: bool,
        relative_filename: Optional[str] = None,  # only used to store `.no_exists` in cache
        storage_folder: Optional[str] = None,  # only used to store `.no_exists` in cache
    ) -> Union[
        # Either an exception is caught and returned
        Tuple[None, None, None, None, Exception],
        # Or the metadata is returned as
        # `(url_to_download, etag, commit_hash, expected_size, None)`
        Tuple[str, str, str, int, None],
    ]:
        """Get metadata for a file on the Hub, safely handling network issues.
    
        Returns either the etag, commit_hash and expected size of the file, or the error
        raised while fetching the metadata.
    
        NOTE: This function mutates `headers` inplace! It removes the `authorization` header
              if the file is a LFS blob and the domain of the url is different from the
              domain of the location (typically an S3 bucket).
        """
        if local_files_only:
            return (
                None,
                None,
                None,
                None,
                OfflineModeIsEnabled(
                    f"Cannot access file since 'local_files_only=True' as been set. (repo_id: {repo_id}, repo_type: {repo_type}, revision: {revision}, filename: {filename})"
                ),
            )
    
        url = hf_hub_url(repo_id, filename, repo_type=repo_type, revision=revision, endpoint=endpoint)
        url_to_download: str = url
        etag: Optional[str] = None
        commit_hash: Optional[str] = None
        expected_size: Optional[int] = None
        head_error_call: Optional[Exception] = None
    
        # Try to get metadata from the server.
        # Do not raise yet if the file is not found or not accessible.
        if not local_files_only:
            try:
                try:
>                   metadata = get_hf_file_metadata(
                        url=url, proxies=proxies, timeout=etag_timeout, headers=headers, token=token
                    )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1374: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ()
kwargs = {'headers': {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0;...3f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10, 'token': None, ...}
has_token = False, arg_name = 'token', arg_value = None

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

url = 'https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json'
token = None, proxies = None, timeout = 10, library_name = None
library_version = None, user_agent = None
headers = {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; transformers/4.47.0; session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}

    @validate_hf_hub_args
    def get_hf_file_metadata(
        url: str,
        token: Union[bool, str, None] = None,
        proxies: Optional[Dict] = None,
        timeout: Optional[float] = constants.DEFAULT_REQUEST_TIMEOUT,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        user_agent: Union[Dict, str, None] = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> HfFileMetadata:
        """Fetch metadata of a file versioned on the Hub for a given url.
    
        Args:
            url (`str`):
                File url, for example returned by [`hf_hub_url`].
            token (`str` or `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If `False` or `None`, no token is provided.
                    - If a string, it's used as the authentication token.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            timeout (`float`, *optional*, defaults to 10):
                How many seconds to wait for the server to send metadata before giving up.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            A [`HfFileMetadata`] object containing metadata such as location, etag, size and
            commit_hash.
        """
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
        hf_headers["Accept-Encoding"] = "identity"  # prevent any compression => we want to know the real size of the file
    
        # Retrieve metadata
>       r = _request_wrapper(
            method="HEAD",
            url=url,
            headers=hf_headers,
            allow_redirects=False,
            follow_relative_redirects=True,
            proxies=proxies,
            timeout=timeout,
        )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1294: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json'
follow_relative_redirects = True
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
>           response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:278: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json'
follow_relative_redirects = False
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}
response = <Response [401]>

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
            response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )
    
            # If redirection, we redirect only relative paths.
            # This is useful in case of a renamed repository.
            if 300 <= response.status_code <= 399:
                parsed_target = urlparse(response.headers["Location"])
                if parsed_target.netloc == "":
                    # This means it is a relative 'location' headers, as allowed by RFC 7231.
                    # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
                    # We want to follow this relative redirect !
                    #
                    # Highly inspired by `resolve_redirects` from requests library.
                    # See https://github.com/psf/requests/blob/main/requests/sessions.py#L159
                    next_url = urlparse(url)._replace(path=parsed_target.path).geturl()
                    return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params)
            return response
    
        # Perform request and return if status_code is not in the retry list.
        response = get_session().request(method=method, url=url, **params)
>       hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:302: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e69-686765224a9df84c50313d6e;190c776d-d322-4bc8-9f1b-be5aa3c95044)
E               
E               Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json.
E               Access to model meta-llama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'meta-llama/Llama-3.2-1B-Instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_llama3_causal_lm(variant, test_device):
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load model (with tokenizer)
>       tokenizer = download_model(AutoTokenizer.from_pretrained, variant)

forge/test/models/pytorch/text/llama/test_llama3.py:128: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/test/utils.py:15: in download_model
    return download_func(*args, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:878: in from_pretrained
    config = AutoConfig.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1021: in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:590: in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:649: in _get_config_dict
    resolved_config_file = cached_file(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo_id = 'meta-llama/Llama-3.2-1B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
            resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )
        except GatedRepoError as e:
            resolved_file = _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)
            if resolved_file is not None or not _raise_exceptions_for_gated_repo:
                return resolved_file
>           raise EnvironmentError(
                "You are trying to access a gated repo.\nMake sure to have access to it at "
                f"https://huggingface.co/{path_or_repo_id}.\n{str(e)}"
            ) from e
E           OSError: You are trying to access a gated repo.
E           Make sure to have access to it at https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct.
E           401 Client Error. (Request ID: Root=1-67660e69-686765224a9df84c50313d6e;190c776d-d322-4bc8-9f1b-be5aa3c95044)
E           
E           Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json.
E           Access to model meta-llama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:421: OSError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
filename = 'config.json', cache_dir = '/github/home/.cache/huggingface/hub'
force_download = False, resume_download = None, proxies = None, token = None
revision = None, local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
>           resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:403: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ('meta-llama/Meta-Llama-3-8B-Instruct', 'config.json')
kwargs = {'cache_dir': '/github/home/.cache/huggingface/hub', 'force_download': False, 'local_files_only': False, 'proxies': None, ...}
has_token = False, arg_name = 'local_files_only', arg_value = False

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

repo_id = 'meta-llama/Meta-Llama-3-8B-Instruct', filename = 'config.json'

    @validate_hf_hub_args
    def hf_hub_download(
        repo_id: str,
        filename: str,
        *,
        subfolder: Optional[str] = None,
        repo_type: Optional[str] = None,
        revision: Optional[str] = None,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        cache_dir: Union[str, Path, None] = None,
        local_dir: Union[str, Path, None] = None,
        user_agent: Union[Dict, str, None] = None,
        force_download: bool = False,
        proxies: Optional[Dict] = None,
        etag_timeout: float = constants.DEFAULT_ETAG_TIMEOUT,
        token: Union[bool, str, None] = None,
        local_files_only: bool = False,
        headers: Optional[Dict[str, str]] = None,
        endpoint: Optional[str] = None,
        resume_download: Optional[bool] = None,
        force_filename: Optional[str] = None,
        local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
    ) -> str:
        """Download a given file if it's not already present in the local cache.
    
        The new cache file layout looks like this:
        - The cache directory contains one subfolder per repo_id (namespaced by repo type)
        - inside each repo folder:
            - refs is a list of the latest known revision => commit_hash pairs
            - blobs contains the actual file blobs (identified by their git-sha or sha256, depending on
              whether they're LFS files or not)
            - snapshots contains one subfolder per commit, each "commit" contains the subset of the files
              that have been resolved at that particular commit. Each filename is a symlink to the blob
              at that particular commit.
    
        ```
        [  96]  .
        └── [ 160]  models--julien-c--EsperBERTo-small
            ├── [ 160]  blobs
            │   ├── [321M]  403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
            │   ├── [ 398]  7cb18dc9bafbfcf74629a4b760af1b160957a83e
            │   └── [1.4K]  d7edf6bd2a681fb0175f7735299831ee1b22b812
            ├── [  96]  refs
            │   └── [  40]  main
            └── [ 128]  snapshots
                ├── [ 128]  2439f60ef33a0d46d85da5001d52aeda5b00ce9f
                │   ├── [  52]  README.md -> ../../blobs/d7edf6bd2a681fb0175f7735299831ee1b22b812
                │   └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
                └── [ 128]  bbc77c8132af1cc5cf678da3f1ddf2de43606d48
                    ├── [  52]  README.md -> ../../blobs/7cb18dc9bafbfcf74629a4b760af1b160957a83e
                    └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
        ```
    
        If `local_dir` is provided, the file structure from the repo will be replicated in this location. When using this
        option, the `cache_dir` will not be used and a `.cache/huggingface/` folder will be created at the root of `local_dir`
        to store some metadata related to the downloaded files. While this mechanism is not as robust as the main
        cache-system, it's optimized for regularly pulling the latest version of a repository.
    
        Args:
            repo_id (`str`):
                A user or an organization name and a repo name separated by a `/`.
            filename (`str`):
                The name of the file in the repo.
            subfolder (`str`, *optional*):
                An optional value corresponding to a folder inside the model repo.
            repo_type (`str`, *optional*):
                Set to `"dataset"` or `"space"` if downloading from a dataset or space,
                `None` or `"model"` if downloading from a model. Default is `None`.
            revision (`str`, *optional*):
                An optional Git revision id which can be a branch name, a tag, or a
                commit hash.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            cache_dir (`str`, `Path`, *optional*):
                Path to the folder where cached files are stored.
            local_dir (`str` or `Path`, *optional*):
                If provided, the downloaded file will be placed under this directory.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether the file should be downloaded even if it already exists in
                the local cache.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            etag_timeout (`float`, *optional*, defaults to `10`):
                When fetching ETag, how many seconds to wait for the server to send
                data before giving up which is passed to `requests.request`.
            token (`str`, `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If a string, it's used as the authentication token.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, avoid downloading the file and return the path to the
                local cached file if it exists.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            `str`: Local path of file or if networking is off, last version of file cached on disk.
    
        Raises:
            [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it doesn't exist,
                or because it is set to `private` and you do not have access.
            [`~utils.RevisionNotFoundError`]
                If the revision to download from cannot be found.
            [`~utils.EntryNotFoundError`]
                If the file to download cannot be found.
            [`~utils.LocalEntryNotFoundError`]
                If network is disabled or unavailable and file is not found in cache.
            [`EnvironmentError`](https://docs.python.org/3/library/exceptions.html#EnvironmentError)
                If `token=True` but the token cannot be found.
            [`OSError`](https://docs.python.org/3/library/exceptions.html#OSError)
                If ETag cannot be determined.
            [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
                If some parameter value is invalid.
    
        """
        if constants.HF_HUB_ETAG_TIMEOUT != constants.DEFAULT_ETAG_TIMEOUT:
            # Respect environment variable above user value
            etag_timeout = constants.HF_HUB_ETAG_TIMEOUT
    
        if force_filename is not None:
            warnings.warn(
                "The `force_filename` parameter is deprecated as a new caching system, "
                "which keeps the filenames as they are on the Hub, is now in place.",
                FutureWarning,
            )
        if resume_download is not None:
            warnings.warn(
                "`resume_download` is deprecated and will be removed in version 1.0.0. "
                "Downloads always resume when possible. "
                "If you want to force a new download, use `force_download=True`.",
                FutureWarning,
            )
    
        if cache_dir is None:
            cache_dir = constants.HF_HUB_CACHE
        if revision is None:
            revision = constants.DEFAULT_REVISION
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
        if isinstance(local_dir, Path):
            local_dir = str(local_dir)
    
        if subfolder == "":
            subfolder = None
        if subfolder is not None:
            # This is used to create a URL, and not a local path, hence the forward slash.
            filename = f"{subfolder}/{filename}"
    
        if repo_type is None:
            repo_type = "model"
        if repo_type not in constants.REPO_TYPES:
            raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(constants.REPO_TYPES)}")
    
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
    
        if local_dir is not None:
            if local_dir_use_symlinks != "auto":
                warnings.warn(
                    "`local_dir_use_symlinks` parameter is deprecated and will be ignored. "
                    "The process to download files to a local folder has been updated and do "
                    "not rely on symlinks anymore. You only need to pass a destination folder "
                    "as`local_dir`.\n"
                    "For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder."
                )
    
            return _hf_hub_download_to_local_dir(
                # Destination
                local_dir=local_dir,
                # File info
                repo_id=repo_id,
                repo_type=repo_type,
                filename=filename,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                cache_dir=cache_dir,
                force_download=force_download,
                local_files_only=local_files_only,
            )
        else:
>           return _hf_hub_download_to_cache_dir(
                # Destination
                cache_dir=cache_dir,
                # File info
                repo_id=repo_id,
                filename=filename,
                repo_type=repo_type,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                local_files_only=local_files_only,
                force_download=force_download,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:860: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _hf_hub_download_to_cache_dir(
        *,
        # Destination
        cache_dir: str,
        # File info
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        # HTTP info
        endpoint: Optional[str],
        etag_timeout: float,
        headers: Dict[str, str],
        proxies: Optional[Dict],
        token: Optional[Union[bool, str]],
        # Additional options
        local_files_only: bool,
        force_download: bool,
    ) -> str:
        """Download a given file to a cache folder, if not already present.
    
        Method should not be called directly. Please use `hf_hub_download` instead.
        """
        locks_dir = os.path.join(cache_dir, ".locks")
        storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
    
        # cross platform transcription of filename, to be used as a local file path.
        relative_filename = os.path.join(*filename.split("/"))
        if os.name == "nt":
            if relative_filename.startswith("..\\") or "\\..\\" in relative_filename:
                raise ValueError(
                    f"Invalid filename: cannot handle filename '{relative_filename}' on Windows. Please ask the repository"
                    " owner to rename this file."
                )
    
        # if user provides a commit_hash and they already have the file on disk, shortcut everything.
        if REGEX_COMMIT_HASH.match(revision):
            pointer_path = _get_pointer_path(storage_folder, revision, relative_filename)
            if os.path.exists(pointer_path) and not force_download:
                return pointer_path
    
        # Try to get metadata (etag, commit_hash, url, size) from the server.
        # If we can't, a HEAD request error is returned.
        (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error(
            repo_id=repo_id,
            filename=filename,
            repo_type=repo_type,
            revision=revision,
            endpoint=endpoint,
            proxies=proxies,
            etag_timeout=etag_timeout,
            headers=headers,
            token=token,
            local_files_only=local_files_only,
            storage_folder=storage_folder,
            relative_filename=relative_filename,
        )
    
        # etag can be None for several reasons:
        # 1. we passed local_files_only.
        # 2. we don't have a connection
        # 3. Hub is down (HTTP 500, 503, 504)
        # 4. repo is not found -for example private or gated- and invalid/missing token sent
        # 5. Hub is blocked by a firewall or proxy is not set correctly.
        # => Try to get the last downloaded one from the specified revision.
        #
        # If the specified revision is a commit hash, look inside "snapshots".
        # If the specified revision is a branch or tag, look inside "refs".
        if head_call_error is not None:
            # Couldn't make a HEAD call => let's try to find a local file
            if not force_download:
                commit_hash = None
                if REGEX_COMMIT_HASH.match(revision):
                    commit_hash = revision
                else:
                    ref_path = os.path.join(storage_folder, "refs", revision)
                    if os.path.isfile(ref_path):
                        with open(ref_path) as f:
                            commit_hash = f.read()
    
                # Return pointer file if exists
                if commit_hash is not None:
                    pointer_path = _get_pointer_path(storage_folder, commit_hash, relative_filename)
                    if os.path.exists(pointer_path) and not force_download:
                        return pointer_path
    
            # Otherwise, raise appropriate error
>           _raise_on_head_call_error(head_call_error, force_download, local_files_only)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:967: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

head_call_error = GatedRepoError('401 Client Error. (Request ID: Root=1-67660e6a-0603b22218e29c2b31487d7b;6f131876-c327-4e98-a632-a70b2d.../Meta-Llama-3-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.')
force_download = False, local_files_only = False

    def _raise_on_head_call_error(head_call_error: Exception, force_download: bool, local_files_only: bool) -> NoReturn:
        """Raise an appropriate error when the HEAD call failed and we cannot locate a local file."""
    
        # No head call => we cannot force download.
        if force_download:
            if local_files_only:
                raise ValueError("Cannot pass 'force_download=True' and 'local_files_only=True' at the same time.")
            elif isinstance(head_call_error, OfflineModeIsEnabled):
                raise ValueError("Cannot pass 'force_download=True' when offline mode is enabled.") from head_call_error
            else:
                raise ValueError("Force download failed due to the above error.") from head_call_error
    
        # No head call + couldn't find an appropriate file on disk => raise an error.
        if local_files_only:
            raise LocalEntryNotFoundError(
                "Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable"
                " hf.co look-ups and downloads online, set 'local_files_only' to False."
            )
        elif isinstance(head_call_error, RepositoryNotFoundError) or isinstance(head_call_error, GatedRepoError):
            # Repo not found or gated => let's raise the actual error
>           raise head_call_error

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1482: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _get_metadata_or_catch_error(
        *,
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        endpoint: Optional[str],
        proxies: Optional[Dict],
        etag_timeout: Optional[float],
        headers: Dict[str, str],  # mutated inplace!
        token: Union[bool, str, None],
        local_files_only: bool,
        relative_filename: Optional[str] = None,  # only used to store `.no_exists` in cache
        storage_folder: Optional[str] = None,  # only used to store `.no_exists` in cache
    ) -> Union[
        # Either an exception is caught and returned
        Tuple[None, None, None, None, Exception],
        # Or the metadata is returned as
        # `(url_to_download, etag, commit_hash, expected_size, None)`
        Tuple[str, str, str, int, None],
    ]:
        """Get metadata for a file on the Hub, safely handling network issues.
    
        Returns either the etag, commit_hash and expected size of the file, or the error
        raised while fetching the metadata.
    
        NOTE: This function mutates `headers` inplace! It removes the `authorization` header
              if the file is a LFS blob and the domain of the url is different from the
              domain of the location (typically an S3 bucket).
        """
        if local_files_only:
            return (
                None,
                None,
                None,
                None,
                OfflineModeIsEnabled(
                    f"Cannot access file since 'local_files_only=True' as been set. (repo_id: {repo_id}, repo_type: {repo_type}, revision: {revision}, filename: {filename})"
                ),
            )
    
        url = hf_hub_url(repo_id, filename, repo_type=repo_type, revision=revision, endpoint=endpoint)
        url_to_download: str = url
        etag: Optional[str] = None
        commit_hash: Optional[str] = None
        expected_size: Optional[int] = None
        head_error_call: Optional[Exception] = None
    
        # Try to get metadata from the server.
        # Do not raise yet if the file is not found or not accessible.
        if not local_files_only:
            try:
                try:
>                   metadata = get_hf_file_metadata(
                        url=url, proxies=proxies, timeout=etag_timeout, headers=headers, token=token
                    )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1374: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ()
kwargs = {'headers': {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0;...3f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10, 'token': None, ...}
has_token = False, arg_name = 'token', arg_value = None

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

url = 'https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json'
token = None, proxies = None, timeout = 10, library_name = None
library_version = None, user_agent = None
headers = {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; transformers/4.47.0; session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}

    @validate_hf_hub_args
    def get_hf_file_metadata(
        url: str,
        token: Union[bool, str, None] = None,
        proxies: Optional[Dict] = None,
        timeout: Optional[float] = constants.DEFAULT_REQUEST_TIMEOUT,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        user_agent: Union[Dict, str, None] = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> HfFileMetadata:
        """Fetch metadata of a file versioned on the Hub for a given url.
    
        Args:
            url (`str`):
                File url, for example returned by [`hf_hub_url`].
            token (`str` or `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If `False` or `None`, no token is provided.
                    - If a string, it's used as the authentication token.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            timeout (`float`, *optional*, defaults to 10):
                How many seconds to wait for the server to send metadata before giving up.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            A [`HfFileMetadata`] object containing metadata such as location, etag, size and
            commit_hash.
        """
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
        hf_headers["Accept-Encoding"] = "identity"  # prevent any compression => we want to know the real size of the file
    
        # Retrieve metadata
>       r = _request_wrapper(
            method="HEAD",
            url=url,
            headers=hf_headers,
            allow_redirects=False,
            follow_relative_redirects=True,
            proxies=proxies,
            timeout=timeout,
        )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1294: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = True
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
>           response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:278: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = False
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}
response = <Response [401]>

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
            response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )
    
            # If redirection, we redirect only relative paths.
            # This is useful in case of a renamed repository.
            if 300 <= response.status_code <= 399:
                parsed_target = urlparse(response.headers["Location"])
                if parsed_target.netloc == "":
                    # This means it is a relative 'location' headers, as allowed by RFC 7231.
                    # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
                    # We want to follow this relative redirect !
                    #
                    # Highly inspired by `resolve_redirects` from requests library.
                    # See https://github.com/psf/requests/blob/main/requests/sessions.py#L159
                    next_url = urlparse(url)._replace(path=parsed_target.path).geturl()
                    return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params)
            return response
    
        # Perform request and return if status_code is not in the retry list.
        response = get_session().request(method=method, url=url, **params)
>       hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:302: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e6a-0603b22218e29c2b31487d7b;6f131876-c327-4e98-a632-a70b2d17e2e9)
E               
E               Cannot access gated repo for url https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json.
E               Access to model meta-llama/Meta-Llama-3-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'meta-llama/Meta-Llama-3-8B-Instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_llama3_sequence_classification(variant, test_device):
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load model (with tokenizer)
>       tokenizer = download_model(AutoTokenizer.from_pretrained, variant)

forge/test/models/pytorch/text/llama/test_llama3.py:172: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/test/utils.py:15: in download_model
    return download_func(*args, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:878: in from_pretrained
    config = AutoConfig.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1021: in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:590: in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:649: in _get_config_dict
    resolved_config_file = cached_file(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
filename = 'config.json', cache_dir = '/github/home/.cache/huggingface/hub'
force_download = False, resume_download = None, proxies = None, token = None
revision = None, local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
            resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )
        except GatedRepoError as e:
            resolved_file = _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)
            if resolved_file is not None or not _raise_exceptions_for_gated_repo:
                return resolved_file
>           raise EnvironmentError(
                "You are trying to access a gated repo.\nMake sure to have access to it at "
                f"https://huggingface.co/{path_or_repo_id}.\n{str(e)}"
            ) from e
E           OSError: You are trying to access a gated repo.
E           Make sure to have access to it at https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct.
E           401 Client Error. (Request ID: Root=1-67660e6a-0603b22218e29c2b31487d7b;6f131876-c327-4e98-a632-a70b2d17e2e9)
E           
E           Cannot access gated repo for url https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json.
E           Access to model meta-llama/Meta-Llama-3-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:421: OSError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo_id = 'meta-llama/Llama-3.1-8B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
>           resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:403: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ('meta-llama/Llama-3.1-8B-Instruct', 'config.json')
kwargs = {'cache_dir': '/github/home/.cache/huggingface/hub', 'force_download': False, 'local_files_only': False, 'proxies': None, ...}
has_token = False, arg_name = 'local_files_only', arg_value = False

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

repo_id = 'meta-llama/Llama-3.1-8B-Instruct', filename = 'config.json'

    @validate_hf_hub_args
    def hf_hub_download(
        repo_id: str,
        filename: str,
        *,
        subfolder: Optional[str] = None,
        repo_type: Optional[str] = None,
        revision: Optional[str] = None,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        cache_dir: Union[str, Path, None] = None,
        local_dir: Union[str, Path, None] = None,
        user_agent: Union[Dict, str, None] = None,
        force_download: bool = False,
        proxies: Optional[Dict] = None,
        etag_timeout: float = constants.DEFAULT_ETAG_TIMEOUT,
        token: Union[bool, str, None] = None,
        local_files_only: bool = False,
        headers: Optional[Dict[str, str]] = None,
        endpoint: Optional[str] = None,
        resume_download: Optional[bool] = None,
        force_filename: Optional[str] = None,
        local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
    ) -> str:
        """Download a given file if it's not already present in the local cache.
    
        The new cache file layout looks like this:
        - The cache directory contains one subfolder per repo_id (namespaced by repo type)
        - inside each repo folder:
            - refs is a list of the latest known revision => commit_hash pairs
            - blobs contains the actual file blobs (identified by their git-sha or sha256, depending on
              whether they're LFS files or not)
            - snapshots contains one subfolder per commit, each "commit" contains the subset of the files
              that have been resolved at that particular commit. Each filename is a symlink to the blob
              at that particular commit.
    
        ```
        [  96]  .
        └── [ 160]  models--julien-c--EsperBERTo-small
            ├── [ 160]  blobs
            │   ├── [321M]  403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
            │   ├── [ 398]  7cb18dc9bafbfcf74629a4b760af1b160957a83e
            │   └── [1.4K]  d7edf6bd2a681fb0175f7735299831ee1b22b812
            ├── [  96]  refs
            │   └── [  40]  main
            └── [ 128]  snapshots
                ├── [ 128]  2439f60ef33a0d46d85da5001d52aeda5b00ce9f
                │   ├── [  52]  README.md -> ../../blobs/d7edf6bd2a681fb0175f7735299831ee1b22b812
                │   └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
                └── [ 128]  bbc77c8132af1cc5cf678da3f1ddf2de43606d48
                    ├── [  52]  README.md -> ../../blobs/7cb18dc9bafbfcf74629a4b760af1b160957a83e
                    └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
        ```
    
        If `local_dir` is provided, the file structure from the repo will be replicated in this location. When using this
        option, the `cache_dir` will not be used and a `.cache/huggingface/` folder will be created at the root of `local_dir`
        to store some metadata related to the downloaded files. While this mechanism is not as robust as the main
        cache-system, it's optimized for regularly pulling the latest version of a repository.
    
        Args:
            repo_id (`str`):
                A user or an organization name and a repo name separated by a `/`.
            filename (`str`):
                The name of the file in the repo.
            subfolder (`str`, *optional*):
                An optional value corresponding to a folder inside the model repo.
            repo_type (`str`, *optional*):
                Set to `"dataset"` or `"space"` if downloading from a dataset or space,
                `None` or `"model"` if downloading from a model. Default is `None`.
            revision (`str`, *optional*):
                An optional Git revision id which can be a branch name, a tag, or a
                commit hash.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            cache_dir (`str`, `Path`, *optional*):
                Path to the folder where cached files are stored.
            local_dir (`str` or `Path`, *optional*):
                If provided, the downloaded file will be placed under this directory.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether the file should be downloaded even if it already exists in
                the local cache.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            etag_timeout (`float`, *optional*, defaults to `10`):
                When fetching ETag, how many seconds to wait for the server to send
                data before giving up which is passed to `requests.request`.
            token (`str`, `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If a string, it's used as the authentication token.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, avoid downloading the file and return the path to the
                local cached file if it exists.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            `str`: Local path of file or if networking is off, last version of file cached on disk.
    
        Raises:
            [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it doesn't exist,
                or because it is set to `private` and you do not have access.
            [`~utils.RevisionNotFoundError`]
                If the revision to download from cannot be found.
            [`~utils.EntryNotFoundError`]
                If the file to download cannot be found.
            [`~utils.LocalEntryNotFoundError`]
                If network is disabled or unavailable and file is not found in cache.
            [`EnvironmentError`](https://docs.python.org/3/library/exceptions.html#EnvironmentError)
                If `token=True` but the token cannot be found.
            [`OSError`](https://docs.python.org/3/library/exceptions.html#OSError)
                If ETag cannot be determined.
            [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
                If some parameter value is invalid.
    
        """
        if constants.HF_HUB_ETAG_TIMEOUT != constants.DEFAULT_ETAG_TIMEOUT:
            # Respect environment variable above user value
            etag_timeout = constants.HF_HUB_ETAG_TIMEOUT
    
        if force_filename is not None:
            warnings.warn(
                "The `force_filename` parameter is deprecated as a new caching system, "
                "which keeps the filenames as they are on the Hub, is now in place.",
                FutureWarning,
            )
        if resume_download is not None:
            warnings.warn(
                "`resume_download` is deprecated and will be removed in version 1.0.0. "
                "Downloads always resume when possible. "
                "If you want to force a new download, use `force_download=True`.",
                FutureWarning,
            )
    
        if cache_dir is None:
            cache_dir = constants.HF_HUB_CACHE
        if revision is None:
            revision = constants.DEFAULT_REVISION
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
        if isinstance(local_dir, Path):
            local_dir = str(local_dir)
    
        if subfolder == "":
            subfolder = None
        if subfolder is not None:
            # This is used to create a URL, and not a local path, hence the forward slash.
            filename = f"{subfolder}/{filename}"
    
        if repo_type is None:
            repo_type = "model"
        if repo_type not in constants.REPO_TYPES:
            raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(constants.REPO_TYPES)}")
    
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
    
        if local_dir is not None:
            if local_dir_use_symlinks != "auto":
                warnings.warn(
                    "`local_dir_use_symlinks` parameter is deprecated and will be ignored. "
                    "The process to download files to a local folder has been updated and do "
                    "not rely on symlinks anymore. You only need to pass a destination folder "
                    "as`local_dir`.\n"
                    "For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder."
                )
    
            return _hf_hub_download_to_local_dir(
                # Destination
                local_dir=local_dir,
                # File info
                repo_id=repo_id,
                repo_type=repo_type,
                filename=filename,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                cache_dir=cache_dir,
                force_download=force_download,
                local_files_only=local_files_only,
            )
        else:
>           return _hf_hub_download_to_cache_dir(
                # Destination
                cache_dir=cache_dir,
                # File info
                repo_id=repo_id,
                filename=filename,
                repo_type=repo_type,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                local_files_only=local_files_only,
                force_download=force_download,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:860: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _hf_hub_download_to_cache_dir(
        *,
        # Destination
        cache_dir: str,
        # File info
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        # HTTP info
        endpoint: Optional[str],
        etag_timeout: float,
        headers: Dict[str, str],
        proxies: Optional[Dict],
        token: Optional[Union[bool, str]],
        # Additional options
        local_files_only: bool,
        force_download: bool,
    ) -> str:
        """Download a given file to a cache folder, if not already present.
    
        Method should not be called directly. Please use `hf_hub_download` instead.
        """
        locks_dir = os.path.join(cache_dir, ".locks")
        storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
    
        # cross platform transcription of filename, to be used as a local file path.
        relative_filename = os.path.join(*filename.split("/"))
        if os.name == "nt":
            if relative_filename.startswith("..\\") or "\\..\\" in relative_filename:
                raise ValueError(
                    f"Invalid filename: cannot handle filename '{relative_filename}' on Windows. Please ask the repository"
                    " owner to rename this file."
                )
    
        # if user provides a commit_hash and they already have the file on disk, shortcut everything.
        if REGEX_COMMIT_HASH.match(revision):
            pointer_path = _get_pointer_path(storage_folder, revision, relative_filename)
            if os.path.exists(pointer_path) and not force_download:
                return pointer_path
    
        # Try to get metadata (etag, commit_hash, url, size) from the server.
        # If we can't, a HEAD request error is returned.
        (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error(
            repo_id=repo_id,
            filename=filename,
            repo_type=repo_type,
            revision=revision,
            endpoint=endpoint,
            proxies=proxies,
            etag_timeout=etag_timeout,
            headers=headers,
            token=token,
            local_files_only=local_files_only,
            storage_folder=storage_folder,
            relative_filename=relative_filename,
        )
    
        # etag can be None for several reasons:
        # 1. we passed local_files_only.
        # 2. we don't have a connection
        # 3. Hub is down (HTTP 500, 503, 504)
        # 4. repo is not found -for example private or gated- and invalid/missing token sent
        # 5. Hub is blocked by a firewall or proxy is not set correctly.
        # => Try to get the last downloaded one from the specified revision.
        #
        # If the specified revision is a commit hash, look inside "snapshots".
        # If the specified revision is a branch or tag, look inside "refs".
        if head_call_error is not None:
            # Couldn't make a HEAD call => let's try to find a local file
            if not force_download:
                commit_hash = None
                if REGEX_COMMIT_HASH.match(revision):
                    commit_hash = revision
                else:
                    ref_path = os.path.join(storage_folder, "refs", revision)
                    if os.path.isfile(ref_path):
                        with open(ref_path) as f:
                            commit_hash = f.read()
    
                # Return pointer file if exists
                if commit_hash is not None:
                    pointer_path = _get_pointer_path(storage_folder, commit_hash, relative_filename)
                    if os.path.exists(pointer_path) and not force_download:
                        return pointer_path
    
            # Otherwise, raise appropriate error
>           _raise_on_head_call_error(head_call_error, force_download, local_files_only)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:967: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

head_call_error = GatedRepoError('401 Client Error. (Request ID: Root=1-67660e6a-341104852fa3cd287a928741;a622f28d-9963-4634-afb8-6a63c6...ama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.')
force_download = False, local_files_only = False

    def _raise_on_head_call_error(head_call_error: Exception, force_download: bool, local_files_only: bool) -> NoReturn:
        """Raise an appropriate error when the HEAD call failed and we cannot locate a local file."""
    
        # No head call => we cannot force download.
        if force_download:
            if local_files_only:
                raise ValueError("Cannot pass 'force_download=True' and 'local_files_only=True' at the same time.")
            elif isinstance(head_call_error, OfflineModeIsEnabled):
                raise ValueError("Cannot pass 'force_download=True' when offline mode is enabled.") from head_call_error
            else:
                raise ValueError("Force download failed due to the above error.") from head_call_error
    
        # No head call + couldn't find an appropriate file on disk => raise an error.
        if local_files_only:
            raise LocalEntryNotFoundError(
                "Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable"
                " hf.co look-ups and downloads online, set 'local_files_only' to False."
            )
        elif isinstance(head_call_error, RepositoryNotFoundError) or isinstance(head_call_error, GatedRepoError):
            # Repo not found or gated => let's raise the actual error
>           raise head_call_error

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1482: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _get_metadata_or_catch_error(
        *,
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        endpoint: Optional[str],
        proxies: Optional[Dict],
        etag_timeout: Optional[float],
        headers: Dict[str, str],  # mutated inplace!
        token: Union[bool, str, None],
        local_files_only: bool,
        relative_filename: Optional[str] = None,  # only used to store `.no_exists` in cache
        storage_folder: Optional[str] = None,  # only used to store `.no_exists` in cache
    ) -> Union[
        # Either an exception is caught and returned
        Tuple[None, None, None, None, Exception],
        # Or the metadata is returned as
        # `(url_to_download, etag, commit_hash, expected_size, None)`
        Tuple[str, str, str, int, None],
    ]:
        """Get metadata for a file on the Hub, safely handling network issues.
    
        Returns either the etag, commit_hash and expected size of the file, or the error
        raised while fetching the metadata.
    
        NOTE: This function mutates `headers` inplace! It removes the `authorization` header
              if the file is a LFS blob and the domain of the url is different from the
              domain of the location (typically an S3 bucket).
        """
        if local_files_only:
            return (
                None,
                None,
                None,
                None,
                OfflineModeIsEnabled(
                    f"Cannot access file since 'local_files_only=True' as been set. (repo_id: {repo_id}, repo_type: {repo_type}, revision: {revision}, filename: {filename})"
                ),
            )
    
        url = hf_hub_url(repo_id, filename, repo_type=repo_type, revision=revision, endpoint=endpoint)
        url_to_download: str = url
        etag: Optional[str] = None
        commit_hash: Optional[str] = None
        expected_size: Optional[int] = None
        head_error_call: Optional[Exception] = None
    
        # Try to get metadata from the server.
        # Do not raise yet if the file is not found or not accessible.
        if not local_files_only:
            try:
                try:
>                   metadata = get_hf_file_metadata(
                        url=url, proxies=proxies, timeout=etag_timeout, headers=headers, token=token
                    )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1374: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ()
kwargs = {'headers': {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0;...3f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10, 'token': None, ...}
has_token = False, arg_name = 'token', arg_value = None

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

url = 'https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json'
token = None, proxies = None, timeout = 10, library_name = None
library_version = None, user_agent = None
headers = {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; transformers/4.47.0; session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}

    @validate_hf_hub_args
    def get_hf_file_metadata(
        url: str,
        token: Union[bool, str, None] = None,
        proxies: Optional[Dict] = None,
        timeout: Optional[float] = constants.DEFAULT_REQUEST_TIMEOUT,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        user_agent: Union[Dict, str, None] = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> HfFileMetadata:
        """Fetch metadata of a file versioned on the Hub for a given url.
    
        Args:
            url (`str`):
                File url, for example returned by [`hf_hub_url`].
            token (`str` or `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If `False` or `None`, no token is provided.
                    - If a string, it's used as the authentication token.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            timeout (`float`, *optional*, defaults to 10):
                How many seconds to wait for the server to send metadata before giving up.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            A [`HfFileMetadata`] object containing metadata such as location, etag, size and
            commit_hash.
        """
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
        hf_headers["Accept-Encoding"] = "identity"  # prevent any compression => we want to know the real size of the file
    
        # Retrieve metadata
>       r = _request_wrapper(
            method="HEAD",
            url=url,
            headers=hf_headers,
            allow_redirects=False,
            follow_relative_redirects=True,
            proxies=proxies,
            timeout=timeout,
        )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1294: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = True
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
>           response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:278: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json'
follow_relative_redirects = False
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}
response = <Response [401]>

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
            response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )
    
            # If redirection, we redirect only relative paths.
            # This is useful in case of a renamed repository.
            if 300 <= response.status_code <= 399:
                parsed_target = urlparse(response.headers["Location"])
                if parsed_target.netloc == "":
                    # This means it is a relative 'location' headers, as allowed by RFC 7231.
                    # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
                    # We want to follow this relative redirect !
                    #
                    # Highly inspired by `resolve_redirects` from requests library.
                    # See https://github.com/psf/requests/blob/main/requests/sessions.py#L159
                    next_url = urlparse(url)._replace(path=parsed_target.path).geturl()
                    return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params)
            return response
    
        # Perform request and return if status_code is not in the retry list.
        response = get_session().request(method=method, url=url, **params)
>       hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:302: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e6a-341104852fa3cd287a928741;a622f28d-9963-4634-afb8-6a63c617639d)
E               
E               Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json.
E               Access to model meta-llama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'meta-llama/Llama-3.1-8B-Instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_llama3_sequence_classification(variant, test_device):
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load model (with tokenizer)
>       tokenizer = download_model(AutoTokenizer.from_pretrained, variant)

forge/test/models/pytorch/text/llama/test_llama3.py:172: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/test/utils.py:15: in download_model
    return download_func(*args, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:878: in from_pretrained
    config = AutoConfig.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1021: in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:590: in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:649: in _get_config_dict
    resolved_config_file = cached_file(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo_id = 'meta-llama/Llama-3.1-8B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
            resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )
        except GatedRepoError as e:
            resolved_file = _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)
            if resolved_file is not None or not _raise_exceptions_for_gated_repo:
                return resolved_file
>           raise EnvironmentError(
                "You are trying to access a gated repo.\nMake sure to have access to it at "
                f"https://huggingface.co/{path_or_repo_id}.\n{str(e)}"
            ) from e
E           OSError: You are trying to access a gated repo.
E           Make sure to have access to it at https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct.
E           401 Client Error. (Request ID: Root=1-67660e6a-341104852fa3cd287a928741;a622f28d-9963-4634-afb8-6a63c617639d)
E           
E           Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json.
E           Access to model meta-llama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:421: OSError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo_id = 'meta-llama/Llama-3.2-1B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
>           resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:403: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ('meta-llama/Llama-3.2-1B-Instruct', 'config.json')
kwargs = {'cache_dir': '/github/home/.cache/huggingface/hub', 'force_download': False, 'local_files_only': False, 'proxies': None, ...}
has_token = False, arg_name = 'local_files_only', arg_value = False

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

repo_id = 'meta-llama/Llama-3.2-1B-Instruct', filename = 'config.json'

    @validate_hf_hub_args
    def hf_hub_download(
        repo_id: str,
        filename: str,
        *,
        subfolder: Optional[str] = None,
        repo_type: Optional[str] = None,
        revision: Optional[str] = None,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        cache_dir: Union[str, Path, None] = None,
        local_dir: Union[str, Path, None] = None,
        user_agent: Union[Dict, str, None] = None,
        force_download: bool = False,
        proxies: Optional[Dict] = None,
        etag_timeout: float = constants.DEFAULT_ETAG_TIMEOUT,
        token: Union[bool, str, None] = None,
        local_files_only: bool = False,
        headers: Optional[Dict[str, str]] = None,
        endpoint: Optional[str] = None,
        resume_download: Optional[bool] = None,
        force_filename: Optional[str] = None,
        local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
    ) -> str:
        """Download a given file if it's not already present in the local cache.
    
        The new cache file layout looks like this:
        - The cache directory contains one subfolder per repo_id (namespaced by repo type)
        - inside each repo folder:
            - refs is a list of the latest known revision => commit_hash pairs
            - blobs contains the actual file blobs (identified by their git-sha or sha256, depending on
              whether they're LFS files or not)
            - snapshots contains one subfolder per commit, each "commit" contains the subset of the files
              that have been resolved at that particular commit. Each filename is a symlink to the blob
              at that particular commit.
    
        ```
        [  96]  .
        └── [ 160]  models--julien-c--EsperBERTo-small
            ├── [ 160]  blobs
            │   ├── [321M]  403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
            │   ├── [ 398]  7cb18dc9bafbfcf74629a4b760af1b160957a83e
            │   └── [1.4K]  d7edf6bd2a681fb0175f7735299831ee1b22b812
            ├── [  96]  refs
            │   └── [  40]  main
            └── [ 128]  snapshots
                ├── [ 128]  2439f60ef33a0d46d85da5001d52aeda5b00ce9f
                │   ├── [  52]  README.md -> ../../blobs/d7edf6bd2a681fb0175f7735299831ee1b22b812
                │   └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
                └── [ 128]  bbc77c8132af1cc5cf678da3f1ddf2de43606d48
                    ├── [  52]  README.md -> ../../blobs/7cb18dc9bafbfcf74629a4b760af1b160957a83e
                    └── [  76]  pytorch_model.bin -> ../../blobs/403450e234d65943a7dcf7e05a771ce3c92faa84dd07db4ac20f592037a1e4bd
        ```
    
        If `local_dir` is provided, the file structure from the repo will be replicated in this location. When using this
        option, the `cache_dir` will not be used and a `.cache/huggingface/` folder will be created at the root of `local_dir`
        to store some metadata related to the downloaded files. While this mechanism is not as robust as the main
        cache-system, it's optimized for regularly pulling the latest version of a repository.
    
        Args:
            repo_id (`str`):
                A user or an organization name and a repo name separated by a `/`.
            filename (`str`):
                The name of the file in the repo.
            subfolder (`str`, *optional*):
                An optional value corresponding to a folder inside the model repo.
            repo_type (`str`, *optional*):
                Set to `"dataset"` or `"space"` if downloading from a dataset or space,
                `None` or `"model"` if downloading from a model. Default is `None`.
            revision (`str`, *optional*):
                An optional Git revision id which can be a branch name, a tag, or a
                commit hash.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            cache_dir (`str`, `Path`, *optional*):
                Path to the folder where cached files are stored.
            local_dir (`str` or `Path`, *optional*):
                If provided, the downloaded file will be placed under this directory.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether the file should be downloaded even if it already exists in
                the local cache.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            etag_timeout (`float`, *optional*, defaults to `10`):
                When fetching ETag, how many seconds to wait for the server to send
                data before giving up which is passed to `requests.request`.
            token (`str`, `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If a string, it's used as the authentication token.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, avoid downloading the file and return the path to the
                local cached file if it exists.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            `str`: Local path of file or if networking is off, last version of file cached on disk.
    
        Raises:
            [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it doesn't exist,
                or because it is set to `private` and you do not have access.
            [`~utils.RevisionNotFoundError`]
                If the revision to download from cannot be found.
            [`~utils.EntryNotFoundError`]
                If the file to download cannot be found.
            [`~utils.LocalEntryNotFoundError`]
                If network is disabled or unavailable and file is not found in cache.
            [`EnvironmentError`](https://docs.python.org/3/library/exceptions.html#EnvironmentError)
                If `token=True` but the token cannot be found.
            [`OSError`](https://docs.python.org/3/library/exceptions.html#OSError)
                If ETag cannot be determined.
            [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
                If some parameter value is invalid.
    
        """
        if constants.HF_HUB_ETAG_TIMEOUT != constants.DEFAULT_ETAG_TIMEOUT:
            # Respect environment variable above user value
            etag_timeout = constants.HF_HUB_ETAG_TIMEOUT
    
        if force_filename is not None:
            warnings.warn(
                "The `force_filename` parameter is deprecated as a new caching system, "
                "which keeps the filenames as they are on the Hub, is now in place.",
                FutureWarning,
            )
        if resume_download is not None:
            warnings.warn(
                "`resume_download` is deprecated and will be removed in version 1.0.0. "
                "Downloads always resume when possible. "
                "If you want to force a new download, use `force_download=True`.",
                FutureWarning,
            )
    
        if cache_dir is None:
            cache_dir = constants.HF_HUB_CACHE
        if revision is None:
            revision = constants.DEFAULT_REVISION
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
        if isinstance(local_dir, Path):
            local_dir = str(local_dir)
    
        if subfolder == "":
            subfolder = None
        if subfolder is not None:
            # This is used to create a URL, and not a local path, hence the forward slash.
            filename = f"{subfolder}/{filename}"
    
        if repo_type is None:
            repo_type = "model"
        if repo_type not in constants.REPO_TYPES:
            raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(constants.REPO_TYPES)}")
    
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
    
        if local_dir is not None:
            if local_dir_use_symlinks != "auto":
                warnings.warn(
                    "`local_dir_use_symlinks` parameter is deprecated and will be ignored. "
                    "The process to download files to a local folder has been updated and do "
                    "not rely on symlinks anymore. You only need to pass a destination folder "
                    "as`local_dir`.\n"
                    "For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder."
                )
    
            return _hf_hub_download_to_local_dir(
                # Destination
                local_dir=local_dir,
                # File info
                repo_id=repo_id,
                repo_type=repo_type,
                filename=filename,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                cache_dir=cache_dir,
                force_download=force_download,
                local_files_only=local_files_only,
            )
        else:
>           return _hf_hub_download_to_cache_dir(
                # Destination
                cache_dir=cache_dir,
                # File info
                repo_id=repo_id,
                filename=filename,
                repo_type=repo_type,
                revision=revision,
                # HTTP info
                endpoint=endpoint,
                etag_timeout=etag_timeout,
                headers=hf_headers,
                proxies=proxies,
                token=token,
                # Additional options
                local_files_only=local_files_only,
                force_download=force_download,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:860: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _hf_hub_download_to_cache_dir(
        *,
        # Destination
        cache_dir: str,
        # File info
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        # HTTP info
        endpoint: Optional[str],
        etag_timeout: float,
        headers: Dict[str, str],
        proxies: Optional[Dict],
        token: Optional[Union[bool, str]],
        # Additional options
        local_files_only: bool,
        force_download: bool,
    ) -> str:
        """Download a given file to a cache folder, if not already present.
    
        Method should not be called directly. Please use `hf_hub_download` instead.
        """
        locks_dir = os.path.join(cache_dir, ".locks")
        storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
    
        # cross platform transcription of filename, to be used as a local file path.
        relative_filename = os.path.join(*filename.split("/"))
        if os.name == "nt":
            if relative_filename.startswith("..\\") or "\\..\\" in relative_filename:
                raise ValueError(
                    f"Invalid filename: cannot handle filename '{relative_filename}' on Windows. Please ask the repository"
                    " owner to rename this file."
                )
    
        # if user provides a commit_hash and they already have the file on disk, shortcut everything.
        if REGEX_COMMIT_HASH.match(revision):
            pointer_path = _get_pointer_path(storage_folder, revision, relative_filename)
            if os.path.exists(pointer_path) and not force_download:
                return pointer_path
    
        # Try to get metadata (etag, commit_hash, url, size) from the server.
        # If we can't, a HEAD request error is returned.
        (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error(
            repo_id=repo_id,
            filename=filename,
            repo_type=repo_type,
            revision=revision,
            endpoint=endpoint,
            proxies=proxies,
            etag_timeout=etag_timeout,
            headers=headers,
            token=token,
            local_files_only=local_files_only,
            storage_folder=storage_folder,
            relative_filename=relative_filename,
        )
    
        # etag can be None for several reasons:
        # 1. we passed local_files_only.
        # 2. we don't have a connection
        # 3. Hub is down (HTTP 500, 503, 504)
        # 4. repo is not found -for example private or gated- and invalid/missing token sent
        # 5. Hub is blocked by a firewall or proxy is not set correctly.
        # => Try to get the last downloaded one from the specified revision.
        #
        # If the specified revision is a commit hash, look inside "snapshots".
        # If the specified revision is a branch or tag, look inside "refs".
        if head_call_error is not None:
            # Couldn't make a HEAD call => let's try to find a local file
            if not force_download:
                commit_hash = None
                if REGEX_COMMIT_HASH.match(revision):
                    commit_hash = revision
                else:
                    ref_path = os.path.join(storage_folder, "refs", revision)
                    if os.path.isfile(ref_path):
                        with open(ref_path) as f:
                            commit_hash = f.read()
    
                # Return pointer file if exists
                if commit_hash is not None:
                    pointer_path = _get_pointer_path(storage_folder, commit_hash, relative_filename)
                    if os.path.exists(pointer_path) and not force_download:
                        return pointer_path
    
            # Otherwise, raise appropriate error
>           _raise_on_head_call_error(head_call_error, force_download, local_files_only)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:967: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

head_call_error = GatedRepoError('401 Client Error. (Request ID: Root=1-67660e6a-1669a74d52b2d321343d228a;8cc24f44-4955-42c5-bb01-6c1270...ama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.')
force_download = False, local_files_only = False

    def _raise_on_head_call_error(head_call_error: Exception, force_download: bool, local_files_only: bool) -> NoReturn:
        """Raise an appropriate error when the HEAD call failed and we cannot locate a local file."""
    
        # No head call => we cannot force download.
        if force_download:
            if local_files_only:
                raise ValueError("Cannot pass 'force_download=True' and 'local_files_only=True' at the same time.")
            elif isinstance(head_call_error, OfflineModeIsEnabled):
                raise ValueError("Cannot pass 'force_download=True' when offline mode is enabled.") from head_call_error
            else:
                raise ValueError("Force download failed due to the above error.") from head_call_error
    
        # No head call + couldn't find an appropriate file on disk => raise an error.
        if local_files_only:
            raise LocalEntryNotFoundError(
                "Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable"
                " hf.co look-ups and downloads online, set 'local_files_only' to False."
            )
        elif isinstance(head_call_error, RepositoryNotFoundError) or isinstance(head_call_error, GatedRepoError):
            # Repo not found or gated => let's raise the actual error
>           raise head_call_error

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1482: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

    def _get_metadata_or_catch_error(
        *,
        repo_id: str,
        filename: str,
        repo_type: str,
        revision: str,
        endpoint: Optional[str],
        proxies: Optional[Dict],
        etag_timeout: Optional[float],
        headers: Dict[str, str],  # mutated inplace!
        token: Union[bool, str, None],
        local_files_only: bool,
        relative_filename: Optional[str] = None,  # only used to store `.no_exists` in cache
        storage_folder: Optional[str] = None,  # only used to store `.no_exists` in cache
    ) -> Union[
        # Either an exception is caught and returned
        Tuple[None, None, None, None, Exception],
        # Or the metadata is returned as
        # `(url_to_download, etag, commit_hash, expected_size, None)`
        Tuple[str, str, str, int, None],
    ]:
        """Get metadata for a file on the Hub, safely handling network issues.
    
        Returns either the etag, commit_hash and expected size of the file, or the error
        raised while fetching the metadata.
    
        NOTE: This function mutates `headers` inplace! It removes the `authorization` header
              if the file is a LFS blob and the domain of the url is different from the
              domain of the location (typically an S3 bucket).
        """
        if local_files_only:
            return (
                None,
                None,
                None,
                None,
                OfflineModeIsEnabled(
                    f"Cannot access file since 'local_files_only=True' as been set. (repo_id: {repo_id}, repo_type: {repo_type}, revision: {revision}, filename: {filename})"
                ),
            )
    
        url = hf_hub_url(repo_id, filename, repo_type=repo_type, revision=revision, endpoint=endpoint)
        url_to_download: str = url
        etag: Optional[str] = None
        commit_hash: Optional[str] = None
        expected_size: Optional[int] = None
        head_error_call: Optional[Exception] = None
    
        # Try to get metadata from the server.
        # Do not raise yet if the file is not found or not accessible.
        if not local_files_only:
            try:
                try:
>                   metadata = get_hf_file_metadata(
                        url=url, proxies=proxies, timeout=etag_timeout, headers=headers, token=token
                    )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1374: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

args = ()
kwargs = {'headers': {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0;...3f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10, 'token': None, ...}
has_token = False, arg_name = 'token', arg_value = None

    @wraps(fn)
    def _inner_fn(*args, **kwargs):
        has_token = False
        for arg_name, arg_value in chain(
            zip(signature.parameters, args),  # Args values
            kwargs.items(),  # Kwargs values
        ):
            if arg_name in ["repo_id", "from_id", "to_id"]:
                validate_repo_id(arg_value)
    
            elif arg_name == "token" and arg_value is not None:
                has_token = True
    
        if check_use_auth_token:
            kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
    
>       return fn(*args, **kwargs)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:114: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

url = 'https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json'
token = None, proxies = None, timeout = 10, library_name = None
library_version = None, user_agent = None
headers = {'user-agent': 'unknown/None; hf_hub/0.27.0; python/3.10.12; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; transformers/4.47.0; session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}

    @validate_hf_hub_args
    def get_hf_file_metadata(
        url: str,
        token: Union[bool, str, None] = None,
        proxies: Optional[Dict] = None,
        timeout: Optional[float] = constants.DEFAULT_REQUEST_TIMEOUT,
        library_name: Optional[str] = None,
        library_version: Optional[str] = None,
        user_agent: Union[Dict, str, None] = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> HfFileMetadata:
        """Fetch metadata of a file versioned on the Hub for a given url.
    
        Args:
            url (`str`):
                File url, for example returned by [`hf_hub_url`].
            token (`str` or `bool`, *optional*):
                A token to be used for the download.
                    - If `True`, the token is read from the HuggingFace config
                      folder.
                    - If `False` or `None`, no token is provided.
                    - If a string, it's used as the authentication token.
            proxies (`dict`, *optional*):
                Dictionary mapping protocol to the URL of the proxy passed to
                `requests.request`.
            timeout (`float`, *optional*, defaults to 10):
                How many seconds to wait for the server to send metadata before giving up.
            library_name (`str`, *optional*):
                The name of the library to which the object corresponds.
            library_version (`str`, *optional*):
                The version of the library.
            user_agent (`dict`, `str`, *optional*):
                The user-agent info in the form of a dictionary or a string.
            headers (`dict`, *optional*):
                Additional headers to be sent with the request.
    
        Returns:
            A [`HfFileMetadata`] object containing metadata such as location, etag, size and
            commit_hash.
        """
        hf_headers = build_hf_headers(
            token=token,
            library_name=library_name,
            library_version=library_version,
            user_agent=user_agent,
            headers=headers,
        )
        hf_headers["Accept-Encoding"] = "identity"  # prevent any compression => we want to know the real size of the file
    
        # Retrieve metadata
>       r = _request_wrapper(
            method="HEAD",
            url=url,
            headers=hf_headers,
            allow_redirects=False,
            follow_relative_redirects=True,
            proxies=proxies,
            timeout=timeout,
        )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1294: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json'
follow_relative_redirects = True
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
>           response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:278: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

method = 'HEAD'
url = 'https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json'
follow_relative_redirects = False
params = {'allow_redirects': False, 'headers': {'Accept-Encoding': 'identity', 'user-agent': 'unknown/None; hf_hub/0.27.0; pyth... session_id/85b7e9c13f9b45b385d075dc2205eb84; file_type/config; from_auto_class/True'}, 'proxies': None, 'timeout': 10}
response = <Response [401]>

    def _request_wrapper(
        method: HTTP_METHOD_T, url: str, *, follow_relative_redirects: bool = False, **params
    ) -> requests.Response:
        """Wrapper around requests methods to follow relative redirects if `follow_relative_redirects=True` even when
        `allow_redirection=False`.
    
        Args:
            method (`str`):
                HTTP method, such as 'GET' or 'HEAD'.
            url (`str`):
                The URL of the resource to fetch.
            follow_relative_redirects (`bool`, *optional*, defaults to `False`)
                If True, relative redirection (redirection to the same site) will be resolved even when `allow_redirection`
                kwarg is set to False. Useful when we want to follow a redirection to a renamed repository without
                following redirection to a CDN.
            **params (`dict`, *optional*):
                Params to pass to `requests.request`.
        """
        # Recursively follow relative redirects
        if follow_relative_redirects:
            response = _request_wrapper(
                method=method,
                url=url,
                follow_relative_redirects=False,
                **params,
            )
    
            # If redirection, we redirect only relative paths.
            # This is useful in case of a renamed repository.
            if 300 <= response.status_code <= 399:
                parsed_target = urlparse(response.headers["Location"])
                if parsed_target.netloc == "":
                    # This means it is a relative 'location' headers, as allowed by RFC 7231.
                    # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
                    # We want to follow this relative redirect !
                    #
                    # Highly inspired by `resolve_redirects` from requests library.
                    # See https://github.com/psf/requests/blob/main/requests/sessions.py#L159
                    next_url = urlparse(url)._replace(path=parsed_target.path).geturl()
                    return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params)
            return response
    
        # Perform request and return if status_code is not in the retry list.
        response = get_session().request(method=method, url=url, **params)
>       hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:302: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e6a-1669a74d52b2d321343d228a;8cc24f44-4955-42c5-bb01-6c12708b3e12)
E               
E               Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json.
E               Access to model meta-llama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'meta-llama/Llama-3.2-1B-Instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_llama3_sequence_classification(variant, test_device):
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Load model (with tokenizer)
>       tokenizer = download_model(AutoTokenizer.from_pretrained, variant)

forge/test/models/pytorch/text/llama/test_llama3.py:172: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/test/utils.py:15: in download_model
    return download_func(*args, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:878: in from_pretrained
    config = AutoConfig.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1021: in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:590: in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/configuration_utils.py:649: in _get_config_dict
    resolved_config_file = cached_file(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo_id = 'meta-llama/Llama-3.2-1B-Instruct', filename = 'config.json'
cache_dir = '/github/home/.cache/huggingface/hub', force_download = False
resume_download = None, proxies = None, token = None, revision = None
local_files_only = False, subfolder = '', repo_type = None
user_agent = 'transformers/4.47.0; python/3.10.12; session_id/85b7e9c13f9b45b385d075dc2205eb84; torch/2.1.0+cpu.cxx11.abi; tensorflow/2.13.0; file_type/config; from_auto_class/True'
_raise_exceptions_for_gated_repo = True
_raise_exceptions_for_missing_entries = True
_raise_exceptions_for_connection_errors = True, _commit_hash = None
deprecated_kwargs = {}, use_auth_token = None, full_filename = 'config.json'
resolved_file = None

    def cached_file(
        path_or_repo_id: Union[str, os.PathLike],
        filename: str,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        resume_download: Optional[bool] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        revision: Optional[str] = None,
        local_files_only: bool = False,
        subfolder: str = "",
        repo_type: Optional[str] = None,
        user_agent: Optional[Union[str, Dict[str, str]]] = None,
        _raise_exceptions_for_gated_repo: bool = True,
        _raise_exceptions_for_missing_entries: bool = True,
        _raise_exceptions_for_connection_errors: bool = True,
        _commit_hash: Optional[str] = None,
        **deprecated_kwargs,
    ) -> Optional[str]:
        """
        Tries to locate a file in a local folder and repo, downloads and cache it if necessary.
    
        Args:
            path_or_repo_id (`str` or `os.PathLike`):
                This can be either:
    
                - a string, the *model id* of a model repo on huggingface.co.
                - a path to a *directory* potentially containing the file.
            filename (`str`):
                The name of the file to locate in `path_or_repo`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
                cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the configuration files and override the cached versions if they
                exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            local_files_only (`bool`, *optional*, defaults to `False`):
                If `True`, will only try to load the tokenizer configuration from local files.
            subfolder (`str`, *optional*, defaults to `""`):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
                specify the folder name here.
            repo_type (`str`, *optional*):
                Specify the repo type (useful when downloading from a space for instance).
    
        <Tip>
    
        Passing `token=True` is required when you want to use a private model.
    
        </Tip>
    
        Returns:
            `Optional[str]`: Returns the resolved file (to the cache folder if downloaded from a repo).
    
        Examples:
    
        ```python
        # Download a model weight from the Hub and cache it.
        model_weights_file = cached_file("google-bert/bert-base-uncased", "pytorch_model.bin")
        ```
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # Private arguments
        #     _raise_exceptions_for_gated_repo: if False, do not raise an exception for gated repo error but return
        #         None.
        #     _raise_exceptions_for_missing_entries: if False, do not raise an exception for missing entries but return
        #         None.
        #     _raise_exceptions_for_connection_errors: if False, do not raise an exception for connection errors but return
        #         None.
        #     _commit_hash: passed when we are chaining several calls to various files (e.g. when loading a tokenizer or
        #         a pipeline). If files are cached for this commit hash, avoid calls to head and get from the cache.
        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True
        if subfolder is None:
            subfolder = ""
    
        path_or_repo_id = str(path_or_repo_id)
        full_filename = os.path.join(subfolder, filename)
        if os.path.isdir(path_or_repo_id):
            resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)
            if not os.path.isfile(resolved_file):
                if _raise_exceptions_for_missing_entries and filename not in ["config.json", f"{subfolder}/config.json"]:
                    raise EnvironmentError(
                        f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
                        f"'https://huggingface.co/{path_or_repo_id}/tree/{revision}' for available files."
                    )
                else:
                    return None
            return resolved_file
    
        if cache_dir is None:
            cache_dir = TRANSFORMERS_CACHE
        if isinstance(cache_dir, Path):
            cache_dir = str(cache_dir)
    
        if _commit_hash is not None and not force_download:
            # If the file is cached under that commit hash, we return it directly.
            resolved_file = try_to_load_from_cache(
                path_or_repo_id, full_filename, cache_dir=cache_dir, revision=_commit_hash, repo_type=repo_type
            )
            if resolved_file is not None:
                if resolved_file is not _CACHED_NO_EXIST:
                    return resolved_file
                elif not _raise_exceptions_for_missing_entries:
                    return None
                else:
                    raise EnvironmentError(f"Could not locate {full_filename} inside {path_or_repo_id}.")
    
        user_agent = http_user_agent(user_agent)
        try:
            # Load from URL or cache if already cached
            resolved_file = hf_hub_download(
                path_or_repo_id,
                filename,
                subfolder=None if len(subfolder) == 0 else subfolder,
                repo_type=repo_type,
                revision=revision,
                cache_dir=cache_dir,
                user_agent=user_agent,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                token=token,
                local_files_only=local_files_only,
            )
        except GatedRepoError as e:
            resolved_file = _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)
            if resolved_file is not None or not _raise_exceptions_for_gated_repo:
                return resolved_file
>           raise EnvironmentError(
                "You are trying to access a gated repo.\nMake sure to have access to it at "
                f"https://huggingface.co/{path_or_repo_id}.\n{str(e)}"
            ) from e
E           OSError: You are trying to access a gated repo.
E           Make sure to have access to it at https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct.
E           401 Client Error. (Request ID: Root=1-67660e6a-1669a74d52b2d321343d228a;8cc24f44-4955-42c5-bb01-6c12708b3e12)
E           
E           Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json.
E           Access to model meta-llama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:421: OSError

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
>           response.raise_for_status()

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:406: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <Response [401]>

    def raise_for_status(self):
        """Raises :class:`HTTPError`, if one occurred."""
    
        http_error_msg = ""
        if isinstance(self.reason, bytes):
            # We attempt to decode utf-8 first because some servers
            # choose to localize their reason strings. If the string
            # isn't utf-8, we fall back to iso-8859-1 for all other
            # encodings. (See PR #3538)
            try:
                reason = self.reason.decode("utf-8")
            except UnicodeDecodeError:
                reason = self.reason.decode("iso-8859-1")
        else:
            reason = self.reason
    
        if 400 <= self.status_code < 500:
            http_error_msg = (
                f"{self.status_code} Client Error: {reason} for url: {self.url}"
            )
    
        elif 500 <= self.status_code < 600:
            http_error_msg = (
                f"{self.status_code} Server Error: {reason} for url: {self.url}"
            )
    
        if http_error_msg:
>           raise HTTPError(http_error_msg, response=self)
E           requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/tf_model.h5

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/requests/models.py:1021: HTTPError

The above exception was the direct cause of the following exception:

path_or_repo = 'mistralai/Mistral-7B-v0.1', filename = 'tf_model.h5'
revision = 'main', proxies = None, token = None, local_files_only = False
cache_dir = None, repo_type = None, deprecated_kwargs = {}
use_auth_token = None, cached_path = None, has_file_in_cache = False
response = <Response [401]>

    def has_file(
        path_or_repo: Union[str, os.PathLike],
        filename: str,
        revision: Optional[str] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        *,
        local_files_only: bool = False,
        cache_dir: Union[str, Path, None] = None,
        repo_type: Optional[str] = None,
        **deprecated_kwargs,
    ):
        """
        Checks if a repo contains a given file without downloading it. Works for remote repos and local folders.
    
        If offline mode is enabled, checks if the file exists in the cache.
    
        <Tip warning={false}>
    
        This function will raise an error if the repository `path_or_repo` is not valid or if `revision` does not exist for
        this repo, but will return False for regular connection errors.
    
        </Tip>
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # If path to local directory, check if the file exists
        if os.path.isdir(path_or_repo):
            return os.path.isfile(os.path.join(path_or_repo, filename))
    
        # Else it's a repo => let's check if the file exists in local cache or on the Hub
    
        # Check if file exists in cache
        # This information might be outdated so it's best to also make a HEAD call (if allowed).
        cached_path = try_to_load_from_cache(
            repo_id=path_or_repo,
            filename=filename,
            revision=revision,
            repo_type=repo_type,
            cache_dir=cache_dir,
        )
        has_file_in_cache = isinstance(cached_path, str)
    
        # If local_files_only, don't try the HEAD call
        if local_files_only:
            return has_file_in_cache
    
        # Check if the file exists
        try:
            response = get_session().head(
                hf_hub_url(path_or_repo, filename=filename, revision=revision, repo_type=repo_type),
                headers=build_hf_headers(token=token, user_agent=http_user_agent()),
                allow_redirects=False,
                proxies=proxies,
                timeout=10,
            )
        except (requests.exceptions.SSLError, requests.exceptions.ProxyError):
            # Actually raise for those subclasses of ConnectionError
            raise
        except (
            requests.exceptions.ConnectionError,
            requests.exceptions.Timeout,
            OfflineModeIsEnabled,
        ):
            return has_file_in_cache
    
        try:
>           hf_raise_for_status(response)

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:676: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

response = <Response [401]>, endpoint_name = None

    def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
        """
        Internal version of `response.raise_for_status()` that will refine a
        potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
    
        This helper is meant to be the unique method to raise_for_status when making a call
        to the Hugging Face Hub.
    
    
        Example:
        ```py
            import requests
            from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError
    
            response = get_session().post(...)
            try:
                hf_raise_for_status(response)
            except HfHubHTTPError as e:
                print(str(e)) # formatted message
                e.request_id, e.server_message # details returned by server
    
                # Complete the error message with additional information once it's raised
                e.append_to_message("\n`create_commit` expects the repository to exist.")
                raise
        ```
    
        Args:
            response (`Response`):
                Response from the server.
            endpoint_name (`str`, *optional*):
                Name of the endpoint that has been called. If provided, the error message
                will be more complete.
    
        <Tip warning={true}>
    
        Raises when the request has failed:
    
            - [`~utils.RepositoryNotFoundError`]
                If the repository to download from cannot be found. This may be because it
                doesn't exist, because `repo_type` is not set correctly, or because the repo
                is `private` and you do not have access.
            - [`~utils.GatedRepoError`]
                If the repository exists but is gated and the user is not on the authorized
                list.
            - [`~utils.RevisionNotFoundError`]
                If the repository exists but the revision couldn't be find.
            - [`~utils.EntryNotFoundError`]
                If the repository exists but the entry (e.g. the requested file) couldn't be
                find.
            - [`~utils.BadRequestError`]
                If request failed with a HTTP 400 BadRequest error.
            - [`~utils.HfHubHTTPError`]
                If request failed for a reason not listed above.
    
        </Tip>
        """
        try:
            response.raise_for_status()
        except HTTPError as e:
            error_code = response.headers.get("X-Error-Code")
            error_message = response.headers.get("X-Error-Message")
    
            if error_code == "RevisionNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
                raise _format(RevisionNotFoundError, message, response) from e
    
            elif error_code == "EntryNotFound":
                message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
                raise _format(EntryNotFoundError, message, response) from e
    
            elif error_code == "GatedRepo":
                message = (
                    f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
                )
>               raise _format(GatedRepoError, message, response) from e
E               huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67660e6b-31599e49400990f55c603670;fd6f7fc7-ab2b-4af1-ac2d-8ec458c72e70)
E               
E               Cannot access gated repo for url https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/tf_model.h5.
E               Access to model mistralai/Mistral-7B-v0.1 is restricted. You must have access to it and be authenticated to access it. Please log in.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py:423: GatedRepoError

The above exception was the direct cause of the following exception:

variant = 'mistralai/Mistral-7B-v0.1', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_mistral(variant, test_device):
    
        configuration = MistralConfig()
    
        configuration.sliding_window = None
        configuration.use_cache = False
        configuration.return_dict = False
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
>       module = AutoModelForCausalLM.from_pretrained(variant, device_map="auto", config=configuration)

forge/test/models/pytorch/text/mistral/test_mistral.py:58: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:564: in from_pretrained
    return model_class.from_pretrained(
/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/modeling_utils.py:3908: in from_pretrained
    if has_file(pretrained_model_name_or_path, TF2_WEIGHTS_NAME, **has_file_kwargs):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

path_or_repo = 'mistralai/Mistral-7B-v0.1', filename = 'tf_model.h5'
revision = 'main', proxies = None, token = None, local_files_only = False
cache_dir = None, repo_type = None, deprecated_kwargs = {}
use_auth_token = None, cached_path = None, has_file_in_cache = False
response = <Response [401]>

    def has_file(
        path_or_repo: Union[str, os.PathLike],
        filename: str,
        revision: Optional[str] = None,
        proxies: Optional[Dict[str, str]] = None,
        token: Optional[Union[bool, str]] = None,
        *,
        local_files_only: bool = False,
        cache_dir: Union[str, Path, None] = None,
        repo_type: Optional[str] = None,
        **deprecated_kwargs,
    ):
        """
        Checks if a repo contains a given file without downloading it. Works for remote repos and local folders.
    
        If offline mode is enabled, checks if the file exists in the cache.
    
        <Tip warning={false}>
    
        This function will raise an error if the repository `path_or_repo` is not valid or if `revision` does not exist for
        this repo, but will return False for regular connection errors.
    
        </Tip>
        """
        use_auth_token = deprecated_kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if token is not None:
                raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
            token = use_auth_token
    
        # If path to local directory, check if the file exists
        if os.path.isdir(path_or_repo):
            return os.path.isfile(os.path.join(path_or_repo, filename))
    
        # Else it's a repo => let's check if the file exists in local cache or on the Hub
    
        # Check if file exists in cache
        # This information might be outdated so it's best to also make a HEAD call (if allowed).
        cached_path = try_to_load_from_cache(
            repo_id=path_or_repo,
            filename=filename,
            revision=revision,
            repo_type=repo_type,
            cache_dir=cache_dir,
        )
        has_file_in_cache = isinstance(cached_path, str)
    
        # If local_files_only, don't try the HEAD call
        if local_files_only:
            return has_file_in_cache
    
        # Check if the file exists
        try:
            response = get_session().head(
                hf_hub_url(path_or_repo, filename=filename, revision=revision, repo_type=repo_type),
                headers=build_hf_headers(token=token, user_agent=http_user_agent()),
                allow_redirects=False,
                proxies=proxies,
                timeout=10,
            )
        except (requests.exceptions.SSLError, requests.exceptions.ProxyError):
            # Actually raise for those subclasses of ConnectionError
            raise
        except (
            requests.exceptions.ConnectionError,
            requests.exceptions.Timeout,
            OfflineModeIsEnabled,
        ):
            return has_file_in_cache
    
        try:
            hf_raise_for_status(response)
            return True
        except GatedRepoError as e:
            logger.error(e)
>           raise EnvironmentError(
                f"{path_or_repo} is a gated repository. Make sure to request access at "
                f"https://huggingface.co/{path_or_repo} and pass a token having permission to this repo either by "
                "logging in with `huggingface-cli login` or by passing `token=<your_token>`."
            ) from e
E           OSError: mistralai/Mistral-7B-v0.1 is a gated repository. Make sure to request access at https://huggingface.co/mistralai/Mistral-7B-v0.1 and pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`.

/opt/ttforge-toolchain/venv/lib/python3.10/site-packages/transformers/utils/hub.py:680: OSError

variant = 'facebook/opt-350m', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_opt_causal_lm(variant, test_device):
        # Load tokenizer and model from HuggingFace
        # Variants: "facebook/opt-125m", "facebook/opt-350m", "facebook/opt-1.3b"
    
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        config = OPTConfig.from_pretrained(variant)
        config_dict = config.to_dict()
        config_dict["return_dict"] = False
        config_dict["use_cache"] = False
        config = OPTConfig(**config_dict)
        model = download_model(OPTForCausalLM.from_pretrained, variant, config=config)
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        tokenizer.pad_token = tokenizer.eos_token
    
        # Input sample
        prefix_text = "My name is Thomas and my main"
        input_tokens = tokenizer(
            prefix_text,
            max_length=256,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
    
        inputs = [input_tokens["input_ids"], input_tokens["attention_mask"]]
>       compiled_model = forge.compile(
            model,
            sample_inputs=inputs,
            module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_")) + "_causal_lm",
        )

forge/test/models/pytorch/text/opt/test_opt.py:42: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

context = CompileContext(modules=[Module pt_opt_350m_causal_lm], graph_name='pt_opt_350m_causal_lm', compiler_cfg=CompilerConfig...in_recompile=False, recompile_count=0, target_cycles_offset=0, forge_module=None, compiled_binary=None, attach_to=None)

    def run_optimization_pass(context: CompileContext) -> CompileDepth:
        """
        Runs optimization passes.
    
        Parameters
        ----------
        context: CompileContext
            Compile context
    
        Returns
        -------
        CompileDepth - next compile stage
        """
        compiler_cfg = context.compiler_cfg
        graph_name = context.graph_name
        graph, intermediate_tensors = context.graph, context.intermediate_tensors
    
>       run_optimization_graph_passes(graph)
E       RuntimeError: TT_ASSERT @ /__w/tt-forge-fe/tt-forge-fe/forge/csrc/passes/commute_utils.cpp:1105: reshape->op_name() == "reshape"
E       info:
E       update_reshape_attr called for a non-reshape operation
E       backtrace:
E        --- tt::passes::update_reshape_attr(tt::graphlib::OpNode*, tt::graphlib::Shape)
E        --- tt::passes::commute_and_bypass(tt::graphlib::Graph*, std::vector<tt::graphlib::Node*, std::allocator<tt::graphlib::Node*> > const&)
E        --- tt::passes::erase_inverse_ops(tt::graphlib::Graph*)
E        --- tt::run_optimization_graph_passes(tt::graphlib::Graph*)
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xfc639) [0x7f4dca9c1639]
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xdf8f5) [0x7f4dca9a48f5]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x18b282) [0x555dce3f2282]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x5c7d) [0x555dce3e1f4d]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0x122) [0x555dce400882]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x818) [0x555dce3dcae8]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0xbb) [0x555dce40081b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]

forge/forge/compile.py:785: RuntimeError

variant = 'facebook/opt-1.3b', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_opt_causal_lm(variant, test_device):
        # Load tokenizer and model from HuggingFace
        # Variants: "facebook/opt-125m", "facebook/opt-350m", "facebook/opt-1.3b"
    
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        config = OPTConfig.from_pretrained(variant)
        config_dict = config.to_dict()
        config_dict["return_dict"] = False
        config_dict["use_cache"] = False
        config = OPTConfig(**config_dict)
        model = download_model(OPTForCausalLM.from_pretrained, variant, config=config)
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        tokenizer.pad_token = tokenizer.eos_token
    
        # Input sample
        prefix_text = "My name is Thomas and my main"
        input_tokens = tokenizer(
            prefix_text,
            max_length=256,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
    
        inputs = [input_tokens["input_ids"], input_tokens["attention_mask"]]
>       compiled_model = forge.compile(
            model,
            sample_inputs=inputs,
            module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_")) + "_causal_lm",
        )

forge/test/models/pytorch/text/opt/test_opt.py:42: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

context = CompileContext(modules=[Module pt_opt_1_3b_causal_lm], graph_name='pt_opt_1_3b_causal_lm', compiler_cfg=CompilerConfig...in_recompile=False, recompile_count=0, target_cycles_offset=0, forge_module=None, compiled_binary=None, attach_to=None)

    def run_optimization_pass(context: CompileContext) -> CompileDepth:
        """
        Runs optimization passes.
    
        Parameters
        ----------
        context: CompileContext
            Compile context
    
        Returns
        -------
        CompileDepth - next compile stage
        """
        compiler_cfg = context.compiler_cfg
        graph_name = context.graph_name
        graph, intermediate_tensors = context.graph, context.intermediate_tensors
    
>       run_optimization_graph_passes(graph)
E       RuntimeError: TT_ASSERT @ /__w/tt-forge-fe/tt-forge-fe/forge/csrc/passes/commute_utils.cpp:1105: reshape->op_name() == "reshape"
E       info:
E       update_reshape_attr called for a non-reshape operation
E       backtrace:
E        --- tt::passes::update_reshape_attr(tt::graphlib::OpNode*, tt::graphlib::Shape)
E        --- tt::passes::commute_and_bypass(tt::graphlib::Graph*, std::vector<tt::graphlib::Node*, std::allocator<tt::graphlib::Node*> > const&)
E        --- tt::passes::erase_inverse_ops(tt::graphlib::Graph*)
E        --- tt::run_optimization_graph_passes(tt::graphlib::Graph*)
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xfc639) [0x7f4dca9c1639]
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xdf8f5) [0x7f4dca9a48f5]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x18b282) [0x555dce3f2282]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x5c7d) [0x555dce3e1f4d]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0x122) [0x555dce400882]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x818) [0x555dce3dcae8]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0xbb) [0x555dce40081b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]

forge/forge/compile.py:785: RuntimeError

variant = 'facebook/opt-125m', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_opt_qa(variant, test_device):
        # Load tokenizer and model from HuggingFace
        # Variants: "facebook/opt-125m", "facebook/opt-350m", "facebook/opt-1.3b"
        # NOTE: These model variants are pre-trined only. They need to be fine-tuned
        # on a downstream task. Code is for demonstration purposes only.
    
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        model = download_model(OPTForQuestionAnswering.from_pretrained, variant, torchscript=True)
    
        # Load data sample
        question, context = "Who was Jim Henson?", "Jim Henson was a nice puppet"
    
        # Data preprocessing
        input_tokens = tokenizer(
            question,
            context,
            max_length=32,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
    
        inputs = [input_tokens["input_ids"], input_tokens["attention_mask"]]
>       compiled_model = forge.compile(
            model,
            sample_inputs=inputs,
            module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_")) + "_qa",
        )

forge/test/models/pytorch/text/opt/test_opt.py:78: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

context = CompileContext(modules=[Module pt_opt_125m_qa], graph_name='pt_opt_125m_qa', compiler_cfg=CompilerConfig(enable_traini...in_recompile=False, recompile_count=0, target_cycles_offset=0, forge_module=None, compiled_binary=None, attach_to=None)

    def run_optimization_pass(context: CompileContext) -> CompileDepth:
        """
        Runs optimization passes.
    
        Parameters
        ----------
        context: CompileContext
            Compile context
    
        Returns
        -------
        CompileDepth - next compile stage
        """
        compiler_cfg = context.compiler_cfg
        graph_name = context.graph_name
        graph, intermediate_tensors = context.graph, context.intermediate_tensors
    
>       run_optimization_graph_passes(graph)
E       RuntimeError: TT_ASSERT @ /__w/tt-forge-fe/tt-forge-fe/forge/csrc/passes/commute_utils.cpp:1105: reshape->op_name() == "reshape"
E       info:
E       update_reshape_attr called for a non-reshape operation
E       backtrace:
E        --- tt::passes::update_reshape_attr(tt::graphlib::OpNode*, tt::graphlib::Shape)
E        --- tt::passes::commute_and_bypass(tt::graphlib::Graph*, std::vector<tt::graphlib::Node*, std::allocator<tt::graphlib::Node*> > const&)
E        --- tt::passes::erase_inverse_ops(tt::graphlib::Graph*)
E        --- tt::run_optimization_graph_passes(tt::graphlib::Graph*)
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xfc639) [0x7f4dca9c1639]
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xdf8f5) [0x7f4dca9a48f5]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x18b282) [0x555dce3f2282]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x5c7d) [0x555dce3e1f4d]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0x122) [0x555dce400882]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x818) [0x555dce3dcae8]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0xbb) [0x555dce40081b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]

forge/forge/compile.py:785: RuntimeError

variant = 'microsoft/phi-3-mini-4k-instruct', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants)
    def test_phi3_causal_lm(variant, test_device):
    
        # Configurations
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        # Phi3Config from pretrained variant, disable return_dict and caching.
        config = Phi3Config.from_pretrained(variant)
        config_dict = config.to_dict()
        config_dict["return_dict"] = False
        config_dict["use_cache"] = False
        config = Phi3Config(**config_dict)
    
        # Load tokenizer and model from HuggingFace
        tokenizer = AutoTokenizer.from_pretrained(variant, return_tensors="pt", trust_remote_code=True)
        tokenizer.add_special_tokens({"pad_token": "[PAD]"})
    
        model = Phi3ForCausalLM.from_pretrained(variant, trust_remote_code=True, config=config)
        model.eval()
    
        # input_prompt
        input_prompt = "Africa is an emerging economy because"
    
        # Tokenize input
        inputs = tokenizer(
            input_prompt,
            return_tensors="pt",
            max_length=256,
            pad_to_max_length=True,
            truncation=True,
        )
    
        input_ids = inputs["input_ids"]
        attn_mask = inputs["attention_mask"]
    
        inputs = [input_ids, attn_mask]
    
>       compiled_model = forge.compile(
            model, sample_inputs=inputs, module_name="pt_" + str(variant.split("/")[-1].replace("-", "_")) + "_causal_lm"
        )

forge/test/models/pytorch/text/phi3/test_phi3.py:59: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
forge/forge/compile.py:634: in generate_initial_graph
    module, module_inputs = convert_to_forge_module(
forge/forge/compile.py:973: in convert_to_forge_module
    forge_module, dev_types, module_inputs = generate_forge_module(
forge/forge/tvm_to_python.py:2076: in generate_forge_module
    module_writers, flattened_inputs = compile_tvm_to_python(
forge/forge/tvm_to_python.py:2168: in compile_tvm_to_python
    json_graphs, flattened_pytorch_inputs, weights = load_tvm_graph(
third_party/tvm/python/tvm/contrib/forge_compile.py:106: in load_tvm_graph
    json_graphs, flattened_inputs = compile_tvm_graph(inputs, module, compiler_cfg, graph_name=graph_name, input_names=input_names, path=path, verify_cfg=verify_cfg, framework=framework)
third_party/tvm/python/tvm/contrib/forge_compile.py:146: in compile_tvm_graph
    json_graphs, inputs = compile_pytorch_for_forge(module, *inputs, graph_name=graph_name, compiler_cfg=compiler_cfg, verify_cfg=verify_cfg, input_names=input_names)
third_party/tvm/python/tvm/contrib/forge_compile.py:372: in compile_pytorch_for_forge
    mod, params = tvm.relay.frontend.from_pytorch(traced_model, input_structure, do_convert_params=convert_params)
third_party/tvm/python/tvm/relay/frontend/pytorch.py:6077: in from_pytorch
    converter.report_missing_conversion(op_names)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <tvm.relay.frontend.pytorch.PyTorchOpConverter object at 0x7f4d7b1523b0>
op_names = {'aten::Int', 'aten::ScalarImplicit', 'aten::add', 'aten::add_', 'aten::arange', 'aten::bitwise_or_', ...}

    def report_missing_conversion(self, op_names):
        """Check if all ops in an input graph are supported by TVM"""
        known_ops = [
            "prim::Constant",
            "prim::GetAttr",
            "prim::ListConstruct",
            "prim::ListUnpack",
            "prim::TupleConstruct",
            "prim::TupleUnpack",
            "prim::RaiseException",
            "prim::If",
            "prim::Loop",
            "prim::DictConstruct",
            "prim::dtype",
            "prim::SetAttr",
            "prim::unchecked_cast"
        ]
        known_ops += list(self.convert_map.keys())
        known_ops += list(qnn_torch.convert_map.keys())
    
        missing = []
    
        for op_name in op_names:
            # Also take care of in-place variant ops like aten::relu_
            if op_name not in known_ops and not (
                op_name.endswith("_") and op_name[:-1] in known_ops
            ):
                missing.append(op_name)
    
        if missing:
            msg = f"The following operators are not implemented: {missing}"
>           raise NotImplementedError(msg)
E           NotImplementedError: The following operators are not implemented: ['aten::bitwise_or_']

third_party/tvm/python/tvm/relay/frontend/pytorch.py:4956: NotImplementedError

variant = 'facebook/xglm-1.7B', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_xglm_causal_lm(variant, test_device):
        # Set Forge configuration parameters
        compiler_cfg = forge.config._get_global_compiler_config()
        compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH
    
        config = XGLMConfig.from_pretrained(variant)
        config_dict = config.to_dict()
        config_dict["return_dict"] = False
        config_dict["use_cache"] = False
        config = XGLMConfig(**config_dict)
        model = download_model(XGLMForCausalLM.from_pretrained, variant, config=config)
        tokenizer = download_model(AutoTokenizer.from_pretrained, variant)
        tokenizer.pad_token = tokenizer.eos_token
    
        # Input sample
        prefix_text = "My name is Thomas and my main"
        input_tokens = tokenizer(
            prefix_text,
            max_length=256,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
    
        inputs = [input_tokens["input_ids"], input_tokens["attention_mask"]]
>       compiled_model = forge.compile(
            model, sample_inputs=inputs, module_name="pt_" + str(variant.split("/")[-1].replace("-", "_").replace(".", "_"))
        )

forge/test/models/pytorch/text/xglm/test_xglm.py:41: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

context = CompileContext(modules=[Module pt_xglm_1_7B], graph_name='pt_xglm_1_7B', compiler_cfg=CompilerConfig(enable_training=F...in_recompile=False, recompile_count=0, target_cycles_offset=0, forge_module=None, compiled_binary=None, attach_to=None)

    def run_optimization_pass(context: CompileContext) -> CompileDepth:
        """
        Runs optimization passes.
    
        Parameters
        ----------
        context: CompileContext
            Compile context
    
        Returns
        -------
        CompileDepth - next compile stage
        """
        compiler_cfg = context.compiler_cfg
        graph_name = context.graph_name
        graph, intermediate_tensors = context.graph, context.intermediate_tensors
    
>       run_optimization_graph_passes(graph)
E       RuntimeError: TT_ASSERT @ /__w/tt-forge-fe/tt-forge-fe/forge/csrc/passes/commute_utils.cpp:1105: reshape->op_name() == "reshape"
E       info:
E       update_reshape_attr called for a non-reshape operation
E       backtrace:
E        --- tt::passes::update_reshape_attr(tt::graphlib::OpNode*, tt::graphlib::Shape)
E        --- tt::passes::commute_and_bypass(tt::graphlib::Graph*, std::vector<tt::graphlib::Node*, std::allocator<tt::graphlib::Node*> > const&)
E        --- tt::passes::erase_inverse_ops(tt::graphlib::Graph*)
E        --- tt::run_optimization_graph_passes(tt::graphlib::Graph*)
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xfc639) [0x7f4dca9c1639]
E        --- /__w/tt-forge-fe/tt-forge-fe/forge/forge/_C.so(+0xdf8f5) [0x7f4dca9a48f5]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x18b282) [0x555dce3f2282]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x5c7d) [0x555dce3e1f4d]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0x122) [0x555dce400882]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x818) [0x555dce3dcae8]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(PyObject_Call+0xbb) [0x555dce40081b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_FastCallDictTstate+0x16d) [0x555dce3e7dbd]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_Call_Prepend+0x5c) [0x555dce3fcd4c]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x29e054) [0x555dce505054]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyObject_MakeTpCall+0x25b) [0x555dce3e8b4b]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x671a) [0x555dce3e29ea]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x6d2) [0x555dce3dc9a2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x2c89) [0x555dce3def59]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x1a22) [0x555dce3ddcf2]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyFunction_Vectorcall+0x7c) [0x555dce3f2aec]
E        --- /opt/ttforge-toolchain/venv/bin/python(_PyEval_EvalFrameDefault+0x58aa) [0x555dce3e1b7a]
E        --- /opt/ttforge-toolchain/venv/bin/python(+0x198be1) [0x555dce3ffbe1]

forge/forge/compile.py:785: RuntimeError

test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    # @pytest.mark.xfail(reason="Failing with pcc=0.82")
    def test_nbeats_with_seasonality_basis(test_device):
        compiler_cfg = forge.config._get_global_compiler_config()
    
        x, x_mask = get_electricity_dataset_input()
    
        pytorch_model = NBeatsWithSeasonalityBasis(
            input_size=72,
            output_size=24,
            num_of_harmonics=1,
            stacks=30,
            layers=4,
            layer_size=2048,
        )
        pytorch_model.eval()
        compiled_model = forge.compile(pytorch_model, sample_inputs=[x, x_mask], module_name="nbeats_seasonality")
        inputs = [x, x_mask]
>       co_out = compiled_model(*inputs)

forge/test/models/pytorch/timeseries/nbeats/test_nbeats.py:38: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <forge.compiled_graph_state.CompiledModel object at 0x7f4e07a96bf0>
inputs = (tensor([[[[ 160.50679,  156.32184,  146.39499,  ...,  264.03345,  169.91641,  163.64682],
          [  79.53951,   85...[1., 1., 1.,  ..., 1., 1., 1.],
          [1., 1., 1.,  ..., 1., 1., 1.],
          [1., 1., 1.,  ..., 1., 1., 1.]]]]))
inputs_and_parameters = [tensor([[[[ 160.50679,  156.32184,  146.39499,  ...,  264.03345,  169.91641,  163.64682],
          [  79.53951,   85...0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]]), ...]

    def __call__(self, *inputs: AnyTensor) -> List[torch.Tensor]:
        """
        Run inference on the compiled model.
    
        Parameters
        ----------
        inputs: [Tensor, ...]
            Input tensors
    
        Returns
        -------
        List[Tensor]
            Output tensors
        """
        self.inputs = [*inputs]
        inputs_and_parameters = [
            *inputs,
            *self.fwd_compiled_graph_state.get_ordered_constant_tensors(),
            *self.fwd_compiled_graph_state.get_ordered_parameter_tensors(),
        ]
    
        if any([not isinstance(t, torch.Tensor) for t in inputs_and_parameters]):
            logger.info("Converting inputs and parameters to PyTorch tensors...")
            inputs_and_parameters = to_pt_tensors(inputs_and_parameters)
    
        if self.training() and isinstance(self.framework_module, PyTorchModule):
            for name, param in self.framework_module.module.named_parameters():
                if param.requires_grad:
                    our_tensor = self.fwd_compiled_graph_state.get_parameter_tensor(name)
    
                    # NOTE: for parameters that require gradients, we want to share the same tensor with the PyTorch module.
                    # This is because we want to be able to optimize the parameters both on the device (through our runtime)
                    # and via the torch optimizers. So this ensures that whichever side updates the parameter value, the other side can see the change.
                    #
                    # This could change in the future, but for now ensure that our premise is correct.
                    assert param is our_tensor
    
        logger.info(
            f"Running model {self.framework_module.get_name()} {self.fwd_compiled_graph_state.graph.get_name()} on device..."
        )
>       all_outputs = run_binary(self.compiled_binary, int(ProgramId.FORWARD), inputs_and_parameters)
E       RuntimeError: Tensor 4 - stride mismatch: expected [24, 1], got [1, 12]

forge/forge/compiled_graph_state.py:273: RuntimeError

variant = 'ese_vovnet39b', test_device = None

    @pytest.mark.nightly
    @pytest.mark.model_analysis
    @pytest.mark.parametrize("variant", variants, ids=variants)
    def test_vovnet_timm_pytorch(variant, test_device):
        model, inputs, _ = generate_model_vovnet_imgcls_timm_pytorch(
            test_device,
            variant,
        )
>       compiled_model = forge.compile(model, sample_inputs=[inputs[0]], module_name=f"pt_{variant}")

forge/test/models/pytorch/vision/vovnet/test_vovnet.py:104: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
forge/forge/compile.py:250: in compile_main
    return forge_compile_from_context(compile_context)
forge/forge/compile.py:292: in forge_compile_from_context
    next_stage = stage_to_func[current_stage](context)
forge/forge/compile.py:785: in run_optimization_pass
    run_optimization_graph_passes(graph)
forge/forge/op/eval/forge/__init__.py:217: in <lambda>
    return lambda *inputs: module_or_class.shape(op_type.op, op_type.attr, *inputs)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

type = 'multiply', attr = [], ops = [[1, 1, 7, 7168], [1, 1, 7, 7]]

    def shape(type, attr, ops) -> Tuple[Tuple, List]:
        assert len(ops) == 2, "Eltwise binary should have two inputs"
    
        if type == "binary_stack":
            dim = attr[0]
            assert ops[0] == ops[1]
            output_shape = list(ops[0])
            output_shape[dim] *= 2
            return tuple(output_shape), []
    
        assert len(attr) == 0, "Eltwise binary should have no attributes"
    
        broadcast = []
        output_shape = []
    
        ops[0] = list(ops[0])
        while len(ops[0]) < len(ops[1]):
            ops[0] = [1] + ops[0]
    
        ops[1] = list(ops[1])
        while len(ops[1]) < len(ops[0]):
            ops[1] = [1] + ops[1]
    
        for dim in range(len(ops[0])):
            if ops[0][dim] != ops[1][dim]:
                if ops[1][dim] == 1:
                    broadcast.append((1, dim - len(ops[1]), ops[0][dim]))  # Convert to negative indexing
                    output_shape.append(ops[0][dim])
                else:
                    assert (
>                       ops[0][dim] == 1
                    ), f"Eltwise binary ops must have the same shape in both inputs, or one operand must be 1 wide to broadcast: {ops[0]} vs {ops[1]}"
E                   AssertionError: Eltwise binary ops must have the same shape in both inputs, or one operand must be 1 wide to broadcast: [1, 1, 7, 7168] vs [1, 1, 7, 7]

forge/forge/op/eval/forge/eltwise_binary.py:91: AssertionError

[XPASS(strict)]