Ki6an/fastT5 · AI Repo StatsKIKi6an/fastT5
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Inference & local LLMPython Apache-2.0 76created 2021-03-11 #deep-learning#fast#fastt5#inference#inference-speed#nlp#onnx#onnxruntime#python#pytorch#quantization#quantized-onnx-models#question-answering#t5#transformer#translation