ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-02-04 21:23:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

[deps] adapt to transformers v5 (#10147)

Browse Source 
Co-authored-by: frozenleaves <frozen@Mac.local>
Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
This commit is contained in:
浮梦
2026-02-02 12:07:19 +08:00
committed by GitHub
parent 762b480131
commit bf04ca6af8
23 changed files with 149 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/train/ppo/workflow.py
View File

@@ -72,7 +72,7 @@ def run_ppo(
ppo_trainer.ppo_train(resume_from_checkpoint=training_args.resume_from_checkpoint)
ppo_trainer.save_model()
if training_args.should_save:
fix_valuehead_checkpoint(model, training_args.output_dir, training_args.save_safetensors)
fix_valuehead_checkpoint(model, training_args.output_dir, getattr(training_args, "save_safetensors", True))
ppo_trainer.save_state() # must be called after save_model to have a folder
if ppo_trainer.is_world_process_zero() and finetuning_args.plot_loss: