Oct 10 19 days ago

1. 14:33

   Fix: Lazy load Llama model inside @spaces.GPU worker to avoid process deadlock Running

   Anoopsingh53
   Verified signature

   cf3fa37
2. 14:27

   Add @spaces.GPU decorator for ZeroGPU

   Anoopsingh53
   Verified signature

   454d84c
3. 14:27

   Add spaces to requirements

   Anoopsingh53
   Verified signature

   6447965
4. 14:23

   Fix: Use pre-built llama-cpp-python wheel to avoid timeout

   Anoopsingh53
   Verified signature

   6e95995
5. 09:41

   Update app.py

   Anoopsingh53
   Verified signature

   cf02e74
6. 09:40

   Update requirements.txt

   Anoopsingh53
   Verified signature

   fcb9c7a
7. 09:32

   Create requirements.txt

   Anoopsingh53
   Verified signature

   d4a3aeb
8. 09:26

   Create app.py

   Anoopsingh53
   Verified signature

   27ecce4
9. 09:25

   Create requirements.txt

   Anoopsingh53
   Verified signature

   ca94ffd
10. 09:24

    initial commit

    Anoopsingh53
    Verified signature

    a1762ba