xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-21 16:47:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[misc] Reduce number of config file requests to HuggingFace (#12797)

Browse Source 
Signed-off-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
This commit is contained in:
Kevin H. Luu 2025-02-06 06:59:18 -08:00 committed by GitHub
parent c786e757fa
commit e152f29502
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 23 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
vllm/transformers_utils/config.py
View File

@ -7,7 +7,7 @@ from pathlib import Path
from typing import Any, Dict, Optional, Type, Union from typing import Any, Dict, Optional, Type, Union
import huggingface_hub import huggingface_hub
from huggingface_hub import (file_exists, hf_hub_download, from huggingface_hub import (file_exists, hf_hub_download, list_repo_files,
try_to_load_from_cache) try_to_load_from_cache)
from huggingface_hub.utils import (EntryNotFoundError, HfHubHTTPError, from huggingface_hub.utils import (EntryNotFoundError, HfHubHTTPError,
LocalEntryNotFoundError, LocalEntryNotFoundError,
@ -395,18 +395,28 @@ def get_sentence_transformer_tokenizer_config(model: str,
- dict: A dictionary containing the configuration parameters - dict: A dictionary containing the configuration parameters
for the Sentence Transformer BERT model. for the Sentence Transformer BERT model.
""" """
for config_name in [ sentence_transformer_config_files = [
"sentence_bert_config.json", "sentence_bert_config.json",
"sentence_roberta_config.json", "sentence_roberta_config.json",
"sentence_distilbert_config.json", "sentence_distilbert_config.json",
"sentence_camembert_config.json", "sentence_camembert_config.json",
"sentence_albert_config.json", "sentence_albert_config.json",
"sentence_xlm-roberta_config.json", "sentence_xlm-roberta_config.json",
"sentence_xlnet_config.json", "sentence_xlnet_config.json",
]: ]
encoder_dict = get_hf_file_to_dict(config_name, model, revision) try:
if encoder_dict: # If model is on HuggingfaceHub, get the repo files
break repo_files = list_repo_files(model, revision=revision, token=HF_TOKEN)
except Exception as e:
logger.debug("Error getting repo files", e)
repo_files = []
encoder_dict = None
for config_name in sentence_transformer_config_files:
if config_name in repo_files or Path(model).exists():
encoder_dict = get_hf_file_to_dict(config_name, model, revision)
if encoder_dict:
break
if not encoder_dict: if not encoder_dict:
return None return None