DLTP_project / README.md

Commit History

Today

  1. model card: stage-2 results with our scorer

    Verified signature
    f63e403
  2. add patch_lora_v2_grpo (stage-2 GRPO adapter, A3 checkpoint-188)

    Verified signature
    117a4d4

Yesterday

  1. readme: stage-2 adapters (patch_lora_v2, patch_lora_v2_sft, patch_lora_v2_grpo)

    Verified signature
    b959f6d

21 days ago

  1. Upload README.md with huggingface_hub

    Verified signature
    655fedf