423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

release v0.6.1

Browse Source
This commit is contained in:
hiyouga
2024-03-29 11:36:08 +08:00
parent c1fe6ce782
commit ca793028c6
5 changed files with 95 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/train/dpo/workflow.py
View File

@@ -28,6 +28,7 @@ def run_dpo(
tokenizer = load_tokenizer(model_args)
dataset = get_dataset(tokenizer, model_args, data_args, training_args, stage="rm")
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
data_collator = DPODataCollatorWithPadding(
tokenizer=tokenizer,
pad_to_multiple_of=8,