Hugging Face's logo

lpv30
/
DL-CK-DPO

Transformers
Safetensors
Model card Files
xet
 Community
DL-CK-DPO

Commit History

  1. Upload processor

    lpv30
    Verified signature
    fcf94f1

  2. DPO fine-tuned from SFT (BERTScore reward)

    lpv30
    Verified signature
    4ace2f3

  3. DPO fine-tuned from SFT (BERTScore reward)

    lpv30
    Verified signature
    ecc16bf

  4. Upload processor

    lpv30
    Verified signature
    88ae1db

  5. DPO fine-tuned from SFT (BERTScore reward)

    lpv30
    Verified signature
    55683b2

  6. initial commit

    lpv30
    Verified signature
    8ea570b