PyMuPDF tqdm gradio Pillow==10.1.0 sentencepiece==0.1.99 numpy==1.26.0 transformers==4.40.2 timm torch==2.1.2 torchvision==0.16.2 https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.2/flash_attn-2.6.2+cu123torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl