1 result found Sort:

Ki6an
fastT5 Ki6an
72
565
apache-2.0
13
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
t5 nlp fast onnx fastt5 python pytorch inference onnxruntime transformer translation quantization deep-learning inference-speed question-answering quantized-onnx-models
Created 2021-03-11
38 commits to master branch, last one 2 years ago