423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 19:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix mixed mm inputs and rlhf-v

Browse Source
This commit is contained in:
hiyouga
2024-09-01 20:52:47 +08:00
parent b5063b4144
commit 9967ccb3ae
20 changed files with 306 additions and 277 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llamafactory/model/loader.py
View File

@@ -25,6 +25,7 @@ from .model_utils.misc import register_autoclass
from .model_utils.mod import convert_pretrained_model_to_mod, load_mod_pretrained_model
from .model_utils.unsloth import load_unsloth_pretrained_model
from .model_utils.valuehead import load_valuehead_params
from .model_utils.visual import get_image_seqlen
from .patcher import patch_config, patch_model, patch_tokenizer, patch_valuehead_model
@@ -65,6 +66,7 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
Note: including inplace operation of model_args.
"""
init_kwargs = _get_init_kwargs(model_args)
config = load_config(model_args)
try:
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path,
@@ -96,6 +98,7 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
try:
processor = AutoProcessor.from_pretrained(model_args.model_name_or_path, **init_kwargs)
setattr(processor, "tokenizer", tokenizer)
setattr(processor, "image_seqlen", get_image_seqlen(config))
except Exception:
processor = None