Adding granite-guardian llamafile

Adding ggml-rocm.dll for llamafile 0.10.2-alpha

Adding ggml-cuda.dll for llamafile 0.10.2-alpha

Adding llamafile 0.10.2-alpha

Delete files *.llamafile ggml-cuda-cublas.dll ggml-cuda-tinyblas.dll ggml-cuda.dll ggml-rocm.dll ggml-vulkan.dll ggml-cuda-cublas.so ggml-cuda-tinyblas.so ggml-cuda.so ggml-rocm.so ggml-vulkan.so llamafile with huggingface_hub

Delete files *.llamafile ggml-cuda-cublas.dll ggml-cuda-tinyblas.dll ggml-cuda.dll ggml-rocm.dll ggml-vulkan.dll ggml-cuda-cublas.so ggml-cuda-tinyblas.so ggml-cuda.so ggml-rocm.so ggml-vulkan.so with huggingface_hub

Delete files *.llamafile with huggingface_hub

Updated README with graduation to release

Upload folder using huggingface_hub

Uploading gemma-4 llamafiles with cuda.so - commit 2db59dc

Adding llamafile executable - commit 2db59dc

Uploading GPU libs - commit 2db59dc

Update README.md

Added README.md for redirect

Removed models - updates will be on the 0.10.0 repo

Updating Qwen models to use cuda-cublas.so, code from commit 3a9a1ea

initial commit