423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 18:20:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] add gpt oss (#8826)

Browse Source
This commit is contained in:
Yaowei Zheng
2025-08-06 05:56:46 +08:00
committed by GitHub
parent 53c98f6f3c
commit 387454e524
10 changed files with 97 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llamafactory/model/loader.py
View File

@@ -156,10 +156,10 @@ def load_model(
if model_args.mixture_of_depths == "load":
model = load_mod_pretrained_model(**init_kwargs)
else:
if type(config) in AutoModelForVision2Seq._model_mapping.keys(): # image-text
load_class = AutoModelForVision2Seq
elif type(config) in AutoModelForImageTextToText._model_mapping.keys(): # image-text
if type(config) in AutoModelForImageTextToText._model_mapping.keys(): # image-text
load_class = AutoModelForImageTextToText
elif type(config) in AutoModelForVision2Seq._model_mapping.keys(): # image-text
load_class = AutoModelForVision2Seq
elif type(config) in AutoModelForSeq2SeqLM._model_mapping.keys(): # audio-text
load_class = AutoModelForSeq2SeqLM
elif type(config) in AutoModelForTextToWaveform._model_mapping.keys(): # audio hack for qwen2_5_omni