test-dpo-001 / README.md
raniero's picture
submission (DPO)
a89ee25 verified

DPO Submission

  • task_id: TEST-DPO-001
  • base_model: mistralai/Mistral-7B-Instruct-v0.2
  • SHA256: 246947b68e373780bbbbf620d7e5aa847cce0a279b2d89fe5616f7bb947a8f71
  • Tags: LoRA, DPO