Skip to content

Commit

Permalink
smaller model
Browse files Browse the repository at this point in the history
  • Loading branch information
SunMarc committed Dec 13, 2023
1 parent 70ac8ce commit 1be2c95
Showing 1 changed file with 8 additions and 10 deletions.
18 changes: 8 additions & 10 deletions tests/quantization/gptq/test_gptq.py
Original file line number Diff line number Diff line change
Expand Up @@ -280,10 +280,10 @@ class GPTQTestActOrderExllama(unittest.TestCase):
"""

EXPECTED_OUTPUTS = set()
EXPECTED_OUTPUTS.add("Hello my name is Katie and I am a 20 year")
model_name = "hf-internal-testing/Llama-2-7B-GPTQ"
revision = "gptq-4bit-128g-actorder_True"
input_text = "Hello my name is"
EXPECTED_OUTPUTS.add("Hello, how are you ? I'm doing good, thanks for asking.")
# 4bit + act_order + 128g
model_name = "hf-internal-testing/TinyLlama-1.1B-Chat-v0.3-GPTQ"
input_text = "Hello, how are you ?"

@classmethod
def setUpClass(cls):
Expand All @@ -293,7 +293,6 @@ def setUpClass(cls):
cls.quantization_config = GPTQConfig(bits=4, max_input_length=4028)
cls.quantized_model = AutoModelForCausalLM.from_pretrained(
cls.model_name,
revision=cls.revision,
torch_dtype=torch.float16,
device_map={"": 0},
quantization_config=cls.quantization_config,
Expand Down Expand Up @@ -356,10 +355,10 @@ class GPTQTestExllamaV2(unittest.TestCase):
"""

EXPECTED_OUTPUTS = set()
EXPECTED_OUTPUTS.add("Hello my name is Katie and I am a 20 year")
model_name = "hf-internal-testing/Llama-2-7B-GPTQ"
revision = "gptq-4bit-128g-actorder_True"
input_text = "Hello my name is"
EXPECTED_OUTPUTS.add("Hello, how are you ? I'm doing good, thanks for asking.")
# 4bit + act_order + 128g
model_name = "hf-internal-testing/TinyLlama-1.1B-Chat-v0.3-GPTQ"
input_text = "Hello, how are you ?"

@classmethod
def setUpClass(cls):
Expand All @@ -369,7 +368,6 @@ def setUpClass(cls):
cls.quantization_config = GPTQConfig(bits=4, exllama_config={"version": 2})
cls.quantized_model = AutoModelForCausalLM.from_pretrained(
cls.model_name,
revision=cls.revision,
torch_dtype=torch.float16,
device_map={"": 0},
quantization_config=cls.quantization_config,
Expand Down

0 comments on commit 1be2c95

Please sign in to comment.