Fix overriding of rope_scaling config (#644)

mosaicml · Oct 3, 2023 · cb1d94a · cb1d94a
1 parent cf015dd
commit cb1d94a
Show file tree

Hide file tree

Showing 2 changed files with 33 additions and 0 deletions.
diff --git a/llmfoundry/models/hf/hf_causal_lm.py b/llmfoundry/models/hf/hf_causal_lm.py
@@ -109,6 +109,7 @@ def __init__(self, om_model_config: Union[DictConfig,
                     )
 
                 attr = getattr(config, k)
+                # attempt to disallow typos in nested configs
                 if isinstance(attr, Mapping):
                     extra_keys = [
                         _k for _k in v.keys() if _k not in attr.keys()
@@ -120,6 +121,10 @@ def __init__(self, om_model_config: Union[DictConfig,
                             f'Expected (a subset of) keys: {list(attr.keys())}.'
                         )
                     getattr(config, k).update(v)
+                # necessary case to allow for rope_scaling to be overriden in llama config
+                elif attr is None and isinstance(v, Mapping):
+                    setattr(config, k, {})
+                    getattr(config, k).update(v)
                 else:
                     setattr(config, k, v)
 

diff --git a/tests/test_hf_config.py b/tests/test_hf_config.py
@@ -1,6 +1,7 @@
 # Copyright 2022 MosaicML LLM Foundry authors
 # SPDX-License-Identifier: Apache-2.0
 
+import os
 import tempfile
 from copy import deepcopy
 from pathlib import Path
@@ -139,3 +140,30 @@ def test_hf_config_override(
                 assert getattr(hf_model.config, k)[_k] == _v
         else:
             assert getattr(hf_model.config, k) == v
+
+
+@pytest.mark.skipif('HUGGING_FACE_HUB_TOKEN' not in os.environ,
+                    reason='CI does not have access to llama2')
+def test_rope_scaling_override():
+    model_cfg = {
+        'name': 'hf_causal_lm',
+        'pretrained_model_name_or_path': 'meta-llama/Llama-2-7b-hf',
+        'config_overrides': {
+            'num_hidden_layers': 2,
+            'hidden_size': 32,
+            'intermediate_size': 64,
+            'rope_scaling': {
+                'type': 'dynamic',
+                'factor': 0.5
+            }
+        },
+        'use_auth_token': True,
+        'pretrained': False,
+        'init_device': 'cpu',
+    }
+    model_cfg = om.create(model_cfg)
+
+    model = COMPOSER_MODEL_REGISTRY[model_cfg.name](model_cfg, tokenizer=None)
+    # This would error if the config isn't parsed into a proper dictionary
+    model.get_metadata()
+    assert model.config.rope_scaling == {'type': 'dynamic', 'factor': 0.5}