Hugging Face's logo

ShaoShuai0605
/
Harness-R1

Reinforcement Learning
Transformers
Safetensors
harness-engineering
agent
supervised-fine-tuning
Model card Files
xet
 Community
Harness-R1 / README.md

Commit History

  1. Add cold-start SFT metadata and inference config

    ShaoShuai0605
    Verified signature
    615b9c3

  1. Document and add Agent-SFT target metadata

    ShaoShuai0605
    Verified signature
    a4184cc

  1. Rename checkpoint folders to harness-r1 and agent-sft-harness-r1

    ShaoShuai0605
    Verified signature
    c1ae038

  2. Simplify model card

    ShaoShuai0605
    Verified signature
    2b06337

  3. Add model card for main-table Harness-R1 checkpoints

    ShaoShuai0605
    Verified signature
    0e26bf9