Add/update the quantized ONNX model files and README.md for Transformers.js v3
#3
by
whitphx
HF Staff
- opened
Applied Quantizations
✅ Based on decoder_with_past_model.onnx with slimming
↳ q4f16 (added)
✅ Based on decoder_model.onnx with slimming
↳ q4f16 (added)
✅ Based on encoder_model.onnx with slimming
↳ q4f16 (added)
✅ Based on decoder_model_merged.onnx without slimming
↳ fp16 (replaced because it was invalid)
↳ q4f16 (added)