Mar 23, 2025

1. 19:21

   Update model.py, change duration to 30

   ninjals
   Verified signature

   b05d419
2. 19:18

   Update model.py, change model to Gemma-2-2b-it.

   ninjals
   Verified signature

   8177792
3. 10:36

   Update model.py, change max_new_tokens to 384

   ninjals
   Verified signature

   e177d74
4. 10:32

   Update model.py, set duration to 50

   ninjals
   Verified signature

   318b794
5. 10:29

   Update model.py, change duration to 35

   ninjals
   Verified signature

   dbb4c63
6. 10:24

   Update model.py, change model to gemma-7b-it

   ninjals
   Verified signature

   6d4ba99
7. 10:17

   Update model.py, change max_new_tokens=512

   ninjals
   Verified signature

   faa8911
8. 10:10

   Add lazy LLM loading to fix ZeroGPU startup

   ninjals
   1bd0027
9. 09:56

   Add lazy LLM loading to fix ZeroGPU startup

   ninjals
   5c22f83
10. 09:43

    Fix ZeroGPU not initialized by lazy loading LLM

    ninjals
    465426d
11. 09:30

    Fix ZeroGPU has not been initialized

    ninjals
    f50eeae
12. 09:15

    Fix SBERT model loading path for embedding model

    ninjals
    6410e01
13. 09:09

    Use HF_TOKEN from Hugging Face Secrets

    ninjals
    860475e
14. 08:03

    Update model.py with secure token loading and device fallback

    ninjals
    2d45581
15. 07:54

    Update model.py

    ninjals
    Verified signature

    dcd121c
16. 07:47

    Update model.py

    ninjals
    Verified signature

    97a9e35
17. 07:45

    update model.py

    ninjals
    Verified signature

    22bb127
18. 07:34

    Update model.py with token = True

    ninjals
    Verified signature

    fcdda62
19. 07:01

    Update model.py, switch model to Gemma-2-2b-it

    ninjals
    Verified signature

    931daaf
20. 06:48

    Update model.py, add device diagnostic code.

    ninjals
    Verified signature

    0a2f11a
21. 05:48

    Add RAG with Gemma and Gradio chatbot interface

    ninjals
    3e314bf