Commit History

  1. Add gguf_file parameter to tokenizer loading and introduce diagnostic script for GGUF validation

    ndc8
    6f81ff7
  2. Fix GGUF filename in environment variable and update comment in requirements

    ndc8
    a2a4e98
  3. Add protobuf requirement for GGUF model loading

    ndc8
    0c37db0
  4. Refactor application to implement GGUF backend with native transformers support; update requirements and add GGUF-specific entry point

    ndc8
    6e96e6e
  5. Refactor model loading to utilize accelerate for device management; add test script to verify loading fix and prevent device conflicts

    ndc8
    8a3c5dd
  6. Refactor application to use lightweight backend; update requirements and add memory analysis script for optimized model configuration

    ndc8
    a4ee3a6
  7. Update Dockerfile and application entry point for GGUF backend; optimize memory usage in model parameters and requirements

    ndc8
    358e717
  8. d

    ndc8
    994c0b4
  9. Refactor backend service to support Gemma 3n model and update requirements; remove obsolete test script and add new dependency tests

    ndc8
    4b4e9ed
  10. c

    ndc8
    4f67c26
  11. b

    ndc8
    557b035
  12. l

    ndc8
    819080c
  13. a

    ndc8
    6496777
  14. Add metadata section to README for project details

    ndc8
    ae13708
  15. aa

    ndc8
    65edee9

  1. Add scripts for converting and generating UltraChat-style SFT dataset⁠

    ndc8
    7ecd130

  1. update

    ndc8
    91181f3
  2. Update Dockerfile: Add missing system dependencies for build

    ndc8
    9fe463f
  3. rabbit-ed

    ndc8
    3960f0f
  4. Cleanup: Remove unnecessary files and update .gitignore

    ndc8
    78b611a

  1. update

    ndc8
    4ecf54e
  2. chg model

    ndc8
    375ade4
  3. change to adapter

    ndc8
    0c9134e
  4. try

    ndc8
    db8cd85
  5. upd

    ndc8
    cb5d5f8
  6. update to use unsloth + mistral

    ndc8
    172b424
  7. change model

    ndc8
    8208c22
  8. try #1

    ndc8
    1ba257c
  9. upd

    ndc8
    8d9c495
  10. update

    ndc8
    3239c69
  11. Fix model dependencies and warnings⁠

    ndc8
    97bafdb
  12. Update model to unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF⁠

    ndc8
    c6f7b75
  13. Revert model back to gemma-3n-E4B-it-GGUF⁠

    ndc8
    88c3c6c
  14. Fix: Update to valid HuggingFace model and fix deprecation warnings⁠

    ndc8
    04d695c
  15. upd

    ndc8
    2cd680b
  16. fix

    ndc8
    255b6fc
  17. fix

    ndc8
    84eb396
  18. update

    ndc8
    e46cec3
  19. upd

    ndc8
    68f41f4
  20. update

    ndc8
    83df634

  1. fix

    ndc8
    4599528
  2. Ignore Hugging Face cache directory

    ndc8
    385d87b
  3. fix

    ndc8
    e6598e6
  4. Add API response endpoint and tests

    ndc8
    09c9042
  5. Set gemma-3n-E4B-it-GGUF as main model for all text generation endpoints

    ndc8
    8d962fd
  6. Update app.py

    Verified signature
    1f4eabe
  7. πŸ”§ Fix HuggingFace Space compatibility⁠

    ndc8
    b6cf19e
  8. πŸš€ Add multimodal AI capabilities with image-text-to-text pipeline⁠

    ndc8
    4e10023
  9. Update space

    ndc8
    d3ad561
  10. initial commit

    Verified signature
    7559c6d