-
Upload README.md with huggingface_hub
-
Upload onnx/decoder_model_merged.onnx with huggingface_hub
-
Upload onnx/decoder_model_merged_quantized.onnx with huggingface_hub
-
Upload generation_config.json with huggingface_hub
-
Upload folder using huggingface_hub
-
Upload 5 files
-
Add INT8 quantized ONNX export for Transformers.js v3
INT8 quantized ONNX encoder + decoder_merged for in-browser inference via Transformers.js v3.
Exported from visheratin/t5-efficient-tiny-grammar-correction with optimum/ONNX runtime, quantized with onnxruntime quantization (dynamic INT8).
encoder: 43MB -> 11MB
decoder: 79MB -> 20MB -
initial commit
