Commit History

  1. fix: replace TinyLlama with Qwen2.5-1.5B-Instruct (provider support)

    Verified signature
    0f21e51
  2. chore: update Dockerfile, TinyLlama converter, vite config for Space⁠

    OnyxlMunkey +1: Cursor
    ecfb822

  1. Sync favored app: TinyLlama/Ollama config, runtime env, UX (tabs, streaming, copy/add, provider dropdown, error actions), Dockerfile and entrypoint⁠

    OnyxlMunkey +1: Cursor
    84cea34
  2. Fix: use /models/{HF_MODEL}/v1/chat/completions path for HF inference proxy

    Verified signature
    e395b6a
  3. Fix: use chat completions API with SmolLM3-3B for HF inference

    Verified signature
    f664740
  4. Fix: replace TinyLlama with SmolLM3-3B (available on hf-inference)

    Verified signature
    c0985da

  1. Harden proxy: safe token sed (#), nginx -t validation, intercept_errors off, safe JSON parse⁠

    OnyxlMunkey +1: Cursor
    0570874
  2. Fix 502: nginx proxy resolver, SSL, timeouts; clearer 401/502 errors⁠

    OnyxlMunkey +1: Cursor
    2611ceb
  3. Fix: use same-origin proxy for HF inference (avoid CORS)

    cc036eb
  4. Text Transformer: Docker app for HF Space⁠

    OnyxlMunkey +1: Cursor
    0f5ca68