kaojai/quickmt-th-en-onnx

QuickMT Thai–English ONNX Q8

This repository contains a Q8 ONNX Runtime conversion of quickmt/quickmt-th-en, prepared by KaoJai.ai for browser-local translation experiments.

The package contains separate Thai source and English target tokenizers, plus quantized encoder and merged-decoder ONNX graphs. It was converted from the upstream EOLE model revision d9a104ed5bcd21f9df89b8d1cfd40a54bd3917b8.

Intended runtime

Use ONNX Runtime Web with an autoregressive decoder loop. This package is not yet compatible with Transformers.js pipeline("translation"), because its merged decoder does not yet expose the key/value-cache interface that generic Transformers.js generation expects.

Files required by the browser runtime:

• onnx/encoder_model_quantized.onnx
• onnx/decoder_model_merged_quantized.onnx
• tokenizer.json and tokenizer_config.json for Thai source text
• target-tokenizer/tokenizer.json and target-tokenizer/tokenizer_config.json for English decoded text

License and attribution

The upstream QuickMT Thai–English model is published by quickmt under CC BY 4.0. KaoJai.ai modified the upstream model by converting its EOLE weights to Q8 ONNX Runtime graphs for browser-local inference. Attribution and source details are in ATTRIBUTION.md.

This conversion does not imply endorsement by quickmt.