biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Default model load/config/tokenizer to mistral format if relevant files exist (#28659)

Browse Source 
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Julien Denize
2025-11-21 22:58:59 +01:00
committed by GitHub
parent c68c7b403d
commit 57430fc95c
15 changed files with 230 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
vllm/transformers_utils/config.py
View File

@@ -1,6 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import fnmatch
import json
import os
import time
@@ -355,6 +356,41 @@ def list_repo_files(
return with_retry(lookup_files, "Error retrieving file list")
def list_filtered_repo_files(
model_name_or_path: str,
allow_patterns: list[str],
revision: str | None = None,
repo_type: str | None = None,
token: str | bool | None = None,
) -> list[str]:
try:
all_files = list_repo_files(
repo_id=model_name_or_path,
revision=revision,
token=token,
repo_type=repo_type,
)
except Exception:
logger.error(
"Error retrieving file list. Please ensure your `model_name_or_path`"
"`repo_type`, `token` and `revision` arguments are correctly set. "
"Returning an empty list."
)
return []
file_list = []
# Filter patterns on filenames
for pattern in allow_patterns:
file_list.extend(
[
file
for file in all_files
if fnmatch.fnmatch(os.path.basename(file), pattern)
]
)
return file_list
def file_exists(
repo_id: str,
file_name: str,
@@ -619,10 +655,14 @@ def get_config(
if config_format == "auto":
try:
if is_gguf or file_or_path_exists(model, HF_CONFIG_NAME, revision=revision):
config_format = "hf"
elif file_or_path_exists(model, MISTRAL_CONFIG_NAME, revision=revision):
# First check for Mistral to avoid defaulting to
# Transformers implementation.
if file_or_path_exists(model, MISTRAL_CONFIG_NAME, revision=revision):
config_format = "mistral"
elif is_gguf or file_or_path_exists(
model, HF_CONFIG_NAME, revision=revision
):
config_format = "hf"
else:
raise ValueError(
"Could not detect config format for no config file found. "