Fetching metadata from the HF Docker repository... 22 days ago
-
ZeroGPU port: transformers + @spaces.GPU instead of the unbuildable llama.cpp build
23 days ago
-
Build llama-cpp-python from source (prebuilt CPU wheels are musl)
-
Pin glibc llama-cpp-python 0.3.2 wheel (0.3.19 wheel is musl)
-
Run SmallThinker locally via llama.cpp GGUF (no provider serves it)
-
InferenceClient (Tiiny/SmallThinker-3B-Preview via providers), sign-in fallback, Gradio 6.29
-
Update README.md
-
adding better error logs
-
Update app.py
-
Update README.md
-
Update README.md
-
Update README.md
-
Update requirements.txt
-
Update app.py
-
Update app.py
-
Update README.md
-
Update app.py
-
Update README.md
-
Update README.md
-
Update README.md
-
3b
-
swapping model to qwen-2.5-72B
-
Update README.md
-
Update app.py
-
Update README.md
-
Update app.py
-
renaming
-
updating to command r
-
Update app.py
-
Update app.py
-
Update README.md
-
Update README.md
-
Update app.py
-
Update README.md
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Update README.md
-
Update app.py
-
Update app.py
-
Update app.py
-
Update README.md
