Add/update the quantized ONNX model files and README.md for Transformers.js v3
#2
by whitphx - opened
Applied Quantizations
✅ Based on decoder_model_merged.onnx with slimming
The base model decoder_model_merged.onnx has been renamed to model.onnx.
↳ ✅ fp16: model_fp16.onnx (added)
↳ ✅ int8: model_int8.onnx (added)
↳ ✅ uint8: model_uint8.onnx (added)
↳ ✅ q4: model_q4.onnx (added)
↳ ✅ q4f16: model_q4f16.onnx (added)
↳ ✅ bnb4: model_bnb4.onnx (added)
Xenova changed pull request status to merged