Commit History

3 days ago

  1. Upload models/grpo_qwen06_merged

    Verified signature
    5c0931f
  2. Upload models/grpo_qwen06

    Verified signature
    8eed597
  3. Upload models/reasoning_warmup_qwen06_merged

    Verified signature
    916382a
  4. Upload models/reasoning_warmup_qwen06

    Verified signature
    6ed71d2

4 days ago

  1. Upload folder using huggingface_hub

    Verified signature
    0f2aeea
  2. Upload full pipeline: CPT/SFT/DPO/warmup/GRPO

    Verified signature
    08c0e0b