release v0.6.1

Former-commit-id: a59d823f554505b2e649e6e111b9dee8306d3ad8
2024-03-29 11:36:08 +08:00
parent 50224b09cc
commit fbd0584391
5 changed files with 95 additions and 57 deletions
--- a/src/llmtuner/train/dpo/workflow.py
+++ b/src/llmtuner/train/dpo/workflow.py
@@ -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,