423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-07-31 10:42:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] do not force load processor (#8457)

Browse Source
This commit is contained in:
Yaowei Zheng 2025-06-25 19:43:00 +08:00 committed by GitHub
parent 6b46c8b689
commit b10333dafb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@ -1,7 +1,7 @@
transformers>=4.45.0,<=4.52.4,!=4.46.*,!=4.47.*,!=4.48.0,!=4.52.0; sys_platform != 'darwin'
transformers>=4.45.0,<=4.51.3,!=4.46.*,!=4.47.*,!=4.48.0,!=4.52.0; sys_platform == 'darwin'
datasets>=2.16.0,<=3.6.0
accelerate>=0.34.0,<=1.7.0
accelerate>=1.3.0,<=1.7.0
peft>=0.14.0,<=0.15.2
trl>=0.8.6,<=0.9.6
tokenizers>=0.19.0,<=0.21.1

2
src/llamafactory/extras/misc.py
View File

@ -98,7 +98,7 @@ def check_dependencies() -> None:
"transformers>=4.45.0,<=4.52.4,!=4.46.0,!=4.46.1,!=4.46.2,!=4.46.3,!=4.47.0,!=4.47.1,!=4.48.0,!=4.52.0"
)
check_version("datasets>=2.16.0,<=3.6.0")
check_version("accelerate>=0.34.0,<=1.7.0")
check_version("accelerate>=1.3.0,<=1.7.0")
check_version("peft>=0.14.0,<=0.15.2")
check_version("trl>=0.8.6,<=0.9.6")
if is_transformers_version_greater_than("4.46.0") and not is_transformers_version_greater_than("4.48.1"):

8
src/llamafactory/model/loader.py
View File

@ -111,9 +111,8 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
**init_kwargs,
)
except Exception as e:
raise OSError("Failed to load processor.") from e
patch_processor(processor, tokenizer, model_args)
logger.info_rank0(f"Failed to load processor: {e}.")
processor = None
# Avoid load tokenizer, see:
# https://github.com/huggingface/transformers/blob/v4.40.0/src/transformers/models/auto/processing_auto.py#L324
@ -121,6 +120,9 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
logger.debug("The loaded processor is not an instance of Processor. Dropping it.")
processor = None
if processor is not None:
patch_processor(processor, tokenizer, model_args)
return {"tokenizer": tokenizer, "processor": processor}