mirror of
https://github.com/huggingface/trl.git
synced 2025-10-20 18:43:52 +08:00
Style
This commit is contained in:
@ -35,7 +35,7 @@ python trl/scripts/dpo.py \
|
||||
--eval_strategy steps \
|
||||
--eval_steps 50 \
|
||||
--output_dir Qwen2-0.5B-DPO \
|
||||
--no_remove_unused_columns
|
||||
--no_remove_unused_columns
|
||||
```
|
||||
|
||||
# LoRA:
|
||||
|
Reference in New Issue
Block a user