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

6
src/llmtuner/train/dpo/workflow.py
View File

@@ -25,11 +25,11 @@ def run_dpo(
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="sft")
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="rm")
data_collator = DPODataCollatorWithPadding(
tokenizer=tokenizer,
pad_to_multiple_of=4,
pad_to_multiple_of=8,
label_pad_token_id=IGNORE_INDEX if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
)
@@ -37,7 +37,7 @@ def run_dpo(
if finetuning_args.ref_model is None and (not training_args.do_train): # use the model itself
ref_model = model
else:
ref_model = create_ref_model(model_args, finetuning_args, stage="dpo")
ref_model = create_ref_model(model_args, finetuning_args)
# Update arguments
training_args_dict = training_args.to_dict()