louis_lifu
/
vllm
mirror of https://github.com/vllm-project/vllm
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Bump transformers to 4.43.2 (#6752)

This commit is contained in:
Michael Goin 2024-07-24 16:22:16 -04:00 committed by GitHub
parent 5448f67635
commit 421e218b37
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 28 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements-common.txt
View File

@ -6,7 +6,7 @@ numpy < 2.0.0
requests
tqdm
py-cpuinfo
transformers >= 4.43.1 # Required for Chameleon and Llama 3.1 hotfox.
transformers >= 4.43.2 # Required for Chameleon and Llama 3.1 hotfox.
tokenizers >= 0.19.1 # Required for Llama 3.
fastapi
aiohttp

53
tests/test_config.py
View File

@ -64,8 +64,9 @@ def test_get_sliding_window():
def test_rope_customization():
TEST_ROPE_SCALING = {"rope_type": "dynamic", "factor": 2.0}
TEST_ROPE_SCALING = {"type": "dynamic", "factor": 2.0}
TEST_ROPE_THETA = 16_000_000.0
LONGCHAT_ROPE_SCALING = {"type": "linear", "factor": 8.0}
llama_model_config = ModelConfig(
"meta-llama/Meta-Llama-3-8B-Instruct",
@ -95,29 +96,29 @@ def test_rope_customization():
None) == TEST_ROPE_THETA
assert llama_model_config.max_model_len == 16384
# TODO: add these back when the rope configs are fixed
# LONGCHAT_ROPE_SCALING = {"rope_type": "linear", "factor": 8.0}
# longchat_model_config = ModelConfig(
# "lmsys/longchat-13b-16k",
# "lmsys/longchat-13b-16k",
# tokenizer_mode="auto",
# trust_remote_code=False,
# dtype="float16",
# seed=0,
# )
# assert getattr(longchat_model_config.hf_config, "rope_scaling",
# None) == LONGCHAT_ROPE_SCALING
# assert longchat_model_config.max_model_len == 16384
longchat_model_config = ModelConfig(
"lmsys/longchat-13b-16k",
"lmsys/longchat-13b-16k",
tokenizer_mode="auto",
trust_remote_code=False,
dtype="float16",
seed=0,
)
# Check if LONGCHAT_ROPE_SCALING entries are in longchat_model_config
assert all(
longchat_model_config.hf_config.rope_scaling.get(key) == value
for key, value in LONGCHAT_ROPE_SCALING.items())
assert longchat_model_config.max_model_len == 16384
# longchat_model_config = ModelConfig(
# "lmsys/longchat-13b-16k",
# "lmsys/longchat-13b-16k",
# tokenizer_mode="auto",
# trust_remote_code=False,
# dtype="float16",
# seed=0,
# rope_scaling=TEST_ROPE_SCALING,
# )
# assert getattr(longchat_model_config.hf_config, "rope_scaling",
# None) == TEST_ROPE_SCALING
# assert longchat_model_config.max_model_len == 4096
longchat_model_config = ModelConfig(
"lmsys/longchat-13b-16k",
"lmsys/longchat-13b-16k",
tokenizer_mode="auto",
trust_remote_code=False,
dtype="float16",
seed=0,
rope_scaling=TEST_ROPE_SCALING,
)
assert getattr(longchat_model_config.hf_config, "rope_scaling",
None) == TEST_ROPE_SCALING
assert longchat_model_config.max_model_len == 4096