Update README.md

README.md

@@ -6,4 +6,18 @@ pipeline_tag: translation
 tags:
 - text2text-generation
 - text-generation-inference
----
+---
+
+## ONNX version of [google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt)
+
+## Converted and quantized with [optimum-cli](https://github.com/huggingface/optimum)
+
+- Convert to ONNX:
+```sh
+optimum-cli onnxruntime export --model google/madlad400-3b-mt <output_path> --legacy
+```
+
+- Quantization:
+```sh
+optimum-cli onnxruntime quantize --onnx_model <input_model_path> -o <output_model_path> --avx512_vnni
+```