423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 11:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2746 from stephen-nju/main

Browse Source 
fix deepspeed ppo RuntimeError
This commit is contained in:
hoshi-hiyouga
2024-03-09 01:37:00 +08:00
committed by GitHub
parent 74ff8664d7 aa71571b77
commit 516d0ddc66
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/model/loader.py
View File

@@ -60,7 +60,7 @@ def load_model(
"""
init_kwargs = _get_init_kwargs(model_args)
config = AutoConfig.from_pretrained(model_args.model_name_or_path, **init_kwargs)
patch_config(config, tokenizer, model_args, init_kwargs, is_trainable)
patch_config(config, tokenizer, model_args,finetuning_args, init_kwargs, is_trainable)
model = None
if is_trainable and model_args.use_unsloth: