metadata
license: apache-2.0
Finetune DPO viethq188/LeoScorpius-7B with ultrafeedback_binarized dataset https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized
You can use alpaca template.
template_format = """{system}
### Instruction:
{prompt}
### Response:
"""