requirements.txt

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

accelerate==0.21.0
colorama
datasets
einops
markdown
numpy
pandas
Pillow>=9.5.0
pyyaml
requests
safetensors==0.3.1
scipy
sentencepiece
tensorboard
tqdm
wandb

git+https://github.com/huggingface/peft@96c0277a1b9a381b10ab34dbf84917f9b3b992e6
git+https://github.com/huggingface/transformers@baf1daa58eb2960248fd9f7c3af0ed245b8ce4af

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"
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.0/auto_gptq-0.4.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.0/auto_gptq-0.4.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

# llama-cpp-python without GPU support
llama-cpp-python==0.1.77; platform_system != "Windows"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.1.77/llama_cpp_python-0.1.77-cp310-cp310-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python with CUDA support
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.77+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-0.1.77+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

# GPTQ-for-LLaMa
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"