datasets
evaluate
git+https://github.com/felipemaiapolo/tinyBenchmarks
immutabledict
langdetect
lm-eval>=0.4.8
nltk>= 3.9.1
numpy==1.26.4
onnx
onnx_ir
onnxruntime
onnxruntime_extensions
onnxruntime_genai>=0.6.0
optimum[onnxruntime]
py7zr
rouge_score
transformers
