torch colorama APScheduler black click datasets gradio gradio_client huggingface-hub matplotlib numpy pandas plotly python-dateutil requests semantic-version tqdm transformers>=4.36.0,<4.37.0 tokenizers>=0.15.0 lm_eval @ git+https://github.com/EleutherAI/lm-evaluation-harness.git accelerate sentencepiece langdetect sacrebleu rouge_score bert-score evaluate spacy selfcheckgpt immutabledict