Commit History

  1. Add four Qwen3-VL-4B GRPO adapters (UI-Genie / AndroidFlux mixes, checkpoint-150) + README section

    Verified signature
    cad3aaa

  1. Add pre_error GRPO LoRA adapters (scalar / discrete), 2026-08-18

    Verified signature
    a90a801

  1. Fix load example: Qwen3-VL needs AutoModelForImageTextToText, not AutoModelForCausalLM

    Verified signature
    6cc8fb3
  2. Add first_error GRPO LoRA adapters (scalar / discrete), 2026-08-17

    Verified signature
    fb502e6
  3. initial commit

    Verified signature
    8e74778