test-dpo-3 / README.md
raniero's picture
submission (DPO)
20bea6a verified

DPO Submission

  • task_id: test-dpo-3
  • base_model: mistralai/Mistral-7B-Instruct-v0.2
  • SHA256: 5c12417e0e51165ea2491e6b6c7f6f26f9930df72bd2f208a70c509e8d1d24e4
  • Tags: LoRA, DPO