requirements.txt

torch==2.2.0
torchvision==0.17.0
transformers==4.46.0
datasets>=2.18.0
peft==0.13.0
trl==0.11.0
bitsandbytes>=0.43.0
accelerate>=0.28.0
huggingface_hub>=0.22.0
safetensors>=0.4.0
# autoawq は量子化時のみ必要（merge_and_quantize.py）