Commit History

  1. increase ctx lenght to 2k

    9ba47d1
  2. increase timeout to 5min

    71d28c5
  3. Code simplification

    248f5a7
  4. Enable speculattive decoding

    a7fdfe6
  5. fix role disorder error in history

    06a162a
  6. Add internet search feature

    4e60755
  7. fix reasonning model's thought process display

    9d3ca6c
  8. bugfix

    4522453
  9. fix for multi-turn conv.

    6c77ec7
  10. bugfix for think tag handling

    14564aa
  11. support reasoning tag

    5db22d5
  12. add missing part of app.py

    afa19a3
  13. fix readme error due to short description length

    1bd76fd
  14. add 4 new models

    d554072
  15. fix error : ValueError: Conversation roles must alternate user/assistant/user/assistant

    3e4847c
  16. upgrade llamacpp version

    b6129d9
  17. fault-free model loading

    6e8312c
  18. add storage indicator

    cc91a1a
  19. improve model management

    0813164
  20. improve storage management

    37ee1f3
  21. fix yaml error

    3190ad6
  22. provide more models, secure memory usage

    cd26609
  23. increase context length to 2048

    56919fd
  24. update readme for 7b

    f746942
  25. switch to 7b model

    ea7adad

  1. switch to 3b q2 model

    88b1f39
  2. Update README.md

    Verified signature
    b5ee7db
  3. adjust thread numbers

    4443d46
  4. switch to 1.5b

    4d633ef
  5. fix model id

    8287454
  6. Add app.py & requirements.txt

    0ff6c39
  7. initial commit

    Verified signature
    ef1afaf