torch
transformers
llama-cpp-python
gradio
requests
sentencepiece
spaces
https://github.com/tridao/flash-attention-wheels/releases/download/v2.3.5.post7/flash_attn_wheels_test-2.3.5.post7+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl