README.md

metadata

license: other
datasets:
  - mlabonne/orpo-dpo-mix-40k
tags:
  - dpo

Daredevil-8B

This is a DPO fine-tune of Daredevil-8-abliterated trained on one epoch of orpo-dpo-mix-40k.

🏆 Evaluation

Open LLM Leaderboard

TBD.

Nous

TBD.

🌳 Model family tree