tzwilliam0
helpful_high
Based on unsloth/qwen2.5-7b-bnb-4bit
Tags
- safetensors
- generated_from_trainer
- unsloth
- trl
- dpo
- arxiv:2305.18290
- endpoints_compatible
- region:us
- Author
- tzwilliam0
- Library
- transformers
- Base model
- unsloth/qwen2.5-7b-bnb-4bit
- Downloads
- 0
- Likes
- 0