evaluate==0.4.3
tqdm==4.67.1
vllm==0.7.3
urllib3==2.3.0
nltk==3.9.1
rouge_score==0.1.2
scikit-learn==1.6.1
langchain==0.3.25
langchain-community==0.3.24
langchain-core==0.3.59
langchain-openai==0.3.30
langdetect
dirtyjson