APScheduler==3.10.1 black==23.11.0 click==8.1.3 datasets==2.14.5 gradio==4.4.0 gradio_client==0.7.0 huggingface-hub>=0.18.0 matplotlib==3.7.1 numpy==1.24.2 pandas==2.0.0 python-dateutil==2.8.2 requests==2.28.2 tqdm==4.65.0 transformers==4.40.0 tokenizers>=0.15.0 git+https://github.com/EleutherAI/lm-evaluation-harness.git@b281b0921b636bc36ad05c0b0b0763bd6dd43463#egg=lm-eval accelerate==0.24.1 sentencepiece qa-metrics