Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 6, 2025
Merged

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

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
506c3b1
p
Feb 6, 2025
d414008
p
Feb 6, 2025
692d1b6
p
Feb 6, 2025
5d851aa
p
Feb 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 23 additions & 13 deletions vllm/transformers_utils/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
from typing import Any, Dict, Optional, Type, Union

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)
from huggingface_hub.utils import (EntryNotFoundError, HfHubHTTPError,
LocalEntryNotFoundError,
Expand Down Expand Up @@ -395,18 +395,28 @@ def get_sentence_transformer_tokenizer_config(model: str,
- dict: A dictionary containing the configuration parameters
for the Sentence Transformer BERT model.
"""
for config_name in [
"sentence_bert_config.json",
"sentence_roberta_config.json",
"sentence_distilbert_config.json",
"sentence_camembert_config.json",
"sentence_albert_config.json",
"sentence_xlm-roberta_config.json",
"sentence_xlnet_config.json",
]:
encoder_dict = get_hf_file_to_dict(config_name, model, revision)
if encoder_dict:
break
sentence_transformer_config_files = [
"sentence_bert_config.json",
"sentence_roberta_config.json",
"sentence_distilbert_config.json",
"sentence_camembert_config.json",
"sentence_albert_config.json",
"sentence_xlm-roberta_config.json",
"sentence_xlnet_config.json",
]
try:
# If model is on HuggingfaceHub, get the repo files
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:
return None
Expand Down