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

tiny fix

Browse Source 
Former-commit-id: d944020257f363f38e62de6279b337e399b7c65e
This commit is contained in:
hiyouga
2024-07-03 02:31:50 +08:00
parent f17ab6ad92
commit a42671c2d7
3 changed files with 17 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -54,7 +54,7 @@ def run_ppo(
reward_model = create_reward_model(model, model_args, finetuning_args)
# Initialize our Trainer
ppo_trainer = CustomPPOTrainer(
ppo_trainer: "CustomPPOTrainer" = CustomPPOTrainer(
model_args=model_args,
training_args=training_args,
finetuning_args=finetuning_args,