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

implement rm server #1543

Browse Source 
Former-commit-id: 2e5bb6888c86079493456c2ddd525f8c52b9963e
This commit is contained in:
hiyouga
2023-12-03 20:52:54 +08:00
parent 4a14099cfd
commit 29545d0e5e
11 changed files with 104 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/train/ppo/workflow.py
View File

@@ -28,14 +28,14 @@ def run_ppo(
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, stage="ppo")
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, add_valuehead=True)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="ppo")
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
# Create reference model and reward model
ref_model = create_ref_model(model_args, finetuning_args, stage="ppo")
ref_model = create_ref_model(model_args, finetuning_args, add_valuehead=True)
reward_model = create_reward_model(model, model_args, finetuning_args)
# Create ppo config