metadata
license: mit
datasets:
- trl-lib/ultrafeedback_binarized
base_model:
- ComparisonPO/Mistral-Instruct-7B-DPO_clean
license: mit
datasets:
- trl-lib/ultrafeedback_binarized
base_model:
- ComparisonPO/Mistral-Instruct-7B-DPO_clean