torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 transformers==4.57.3 trl==0.9.3 deepspeed==0.16.9 https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.6cxx11abiTRUE-cp310-cp310-linux_x86_64.whl peft huggingface_hub bitsandbytes accelerate numpy