live-test-dpo-001 / README.md
raniero's picture
submission (DPO)
aced3a0 verified

DPO Submission

  • task_id: live-test-dpo-001
  • base_model: mistralai/Mistral-7B-Instruct-v0.2
  • SHA256: 40c6e8635e4559c6998509c4094ce5ea917dc337d5cc9819b14ebd173c19073f
  • Tags: LoRA, DPO