accelerate==1.8.*
audioop-lts<1.0; python_version >= "3.13"
bitsandbytes==0.48.*
colorama
datasets
einops
fastapi==0.112.4
flash-linear-attention==0.3.2
html2text==2025.4.15
jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.11.0
PyPDF2==3.0.1
python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.57.*
triton-windows==3.3.1.post19; platform_system == "Windows"
tqdm
wandb

# Gradio
gradio==4.37.*
https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl

# API
flask_cloudflared==0.0.14
sse-starlette==1.6.5
tiktoken

# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.10/exllamav3-0.0.10+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.10/exllamav3-0.0.10+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.7cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"