Skip to content

Latest commit

 

History

History
30 lines (21 loc) · 471 Bytes

README.md

File metadata and controls

30 lines (21 loc) · 471 Bytes
Raw

onnx-test

Setup steps

1.setup

pip install optimum[exporters,onnxruntime]

2.convert onnx

optimum-cli export onnx --model sentence-transformers/all-MiniLM-L6-v2 all-MiniLM-L6-v2-onnx

Better example

optimum-cli export onnx -m Helsinki-NLP/opus-mt-zh-en --optimize O2 optus-mt-zh-en-onnx

OnnxRuntime

optimum-cli onnxruntime quantize \
  --avx512 \
  --onnx_model bert-tiny-onnx \
  -o quantized_bert-tiny-onnx