aiofiles==23.1.0
fastapi==0.95.2
gradio_client==0.2.5
gradio==3.33.1
pydantic==1.10.12

accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.5; platform_system != "Darwin" and platform_machine != "x86_64"
markdown
numpy==1.24
optimum==1.13.1
pandas
peft==0.5.*
Pillow>=9.5.0
pyyaml
requests
safetensors==0.3.2
scipy
sentencepiece
tensorboard
transformers==4.34.*
tqdm
wandb

git+https://github.com/oobabooga/torch-grammar.git

# bitsandbytes
bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

# llama-cpp-python (CPU only, no AVX2)
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"

# CUDA wheels
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp/exllamav2/releases/download/v0.0.5/exllamav2-0.0.5+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/turboderp/exllamav2/releases/download/v0.0.5/exllamav2-0.0.5+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.0/flash_attn-2.3.0+cu117torch2.0cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu117-py3-none-any.whl
autoawq==0.1.4