🔧 Convert model binaries for Transformers.js v3
#2
by whitphx - opened
This automated migration updates the model repository for Transformers.js v3.
Changes Made:
- Add missing quantized ONNX model variants (fp16, q8, int8, uint8, q4, q4f16, bnb4) for Transformers.js v3
Notes:
This is an automated migration focused on model binaries.
Please review the changes before merging.
Generated by transformers-js-v3-migrator
Perfect!
Xenova changed pull request status to merged