ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix mrope

Browse Source 
Former-commit-id: 55bee1d333549ca19858b3f5c1b7b86926e5fb09
This commit is contained in:
hiyouga
2024-12-12 15:08:17 +00:00
parent cfff136b2a
commit fb22651faf
11 changed files with 32 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -46,7 +46,7 @@ def run_ppo(
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
data_collator = MultiModalDataCollatorForSeq2Seq(template=template, **tokenizer_module)
data_collator = MultiModalDataCollatorForSeq2Seq(template=template, model=model, **tokenizer_module)
# Create reference model and reward model
ref_model = create_ref_model(model_args, finetuning_args, add_valuehead=True)