Hugging Face's logo

Spaces:
FluffyAIcode
/
LLM-KA-Cache-Compress
Sleeping

App Files Community
LLM-KA-Cache-Compress

Commit History

  1. Switch default model to Qwen3-0.6B (head_dim=128, GQA); bump transformers>=4.51

    cryptobiosis
    Verified signature
    23d974d

  2. Drop 'demo' suffix from page title

    cryptobiosis
    Verified signature
    2b572cf

  3. Fix compression-ratio display + switch to repetition-safe default prompt; align with Docker SDK manifest (Dockerfile + requirements.txt + README.md)

    cryptobiosis
    Verified signature
    292780d

  4. Update app.py

    cryptobiosis
    Verified signature
    caaa501

  5. Update README.md

    cryptobiosis
    Verified signature
    3ef5450

  6. Update README.md

    cryptobiosis
    Verified signature
    a80df25

  7. Update app.py

    cryptobiosis
    Verified signature
    73e1f14

  8. Create app.py

    cryptobiosis
    Verified signature
    163f417

  9. Create requirements.txt

    cryptobiosis
    Verified signature
    6c53ae6

  10. Create Dockerfile

    cryptobiosis
    Verified signature
    59805d0

  11. Update README.md

    cryptobiosis
    Verified signature
    3f31c94

  12. initial commit

    cryptobiosis
    Verified signature
    49d3638