423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 03:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

implement rm server #1543

Browse Source
This commit is contained in:
hiyouga
2023-12-03 20:52:54 +08:00
parent 03d05991f8
commit 7df4f3ab20
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/rm/workflow.py
View File

@@ -25,9 +25,9 @@ def run_rm(
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="rm")
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="rm")
data_collator = PairwiseDataCollatorWithPadding(tokenizer, pad_to_multiple_of=4)
data_collator = PairwiseDataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)
# Update arguments
training_args_dict = training_args.to_dict()