benchmark_data.csv

framework,model,chunk size,MRR@10,Hit@10
Transformers,BERT-base,128,0.32,0.45
Transformers,BERT-large,256,0.37,0.50
Fairseq,ROBERTA-base,128,0.35,0.48
Fairseq,ROBERTA-large,256,0.40,0.55
HuggingFace,GPT-2,128,0.30,0.44
HuggingFace,GPT-3,256,0.42,0.57
TensorFlow,T5-small,128,0.31,0.46
TensorFlow,T5-large,256,0.39,0.51
PyTorch,BART-base,128,0.33,0.47
PyTorch,BART-large,256,0.38,0.53