torch==2.1.2
huggingface-hub
packaging==24.0
colossalai==0.3.6
autoflake==2.2.1
black==23.9.1
transformers==4.34.1
tensorboard==2.14.0
six==1.16.0
datasets
ninja==1.11.1
flash-attn>=2.0.0,<=2.0.5
tqdm
sentencepiece==0.1.99
protobuf<=3.20.0