Update README.md

Upgrade to V5: Matryoshka Loss with Asymmetric Weights [1.0, 0.4, 0.2, 0.2]. Minimized truncation tax at 768d.

Upgrade to V4 (Matryoshka Tuned Weights). 768d: 0.8427 | 128d: 0.8005

Update README.md

Update README.md

Upgrade to V4: Matryoshka Loss with Asymmetric Weights [1.0, 0.3, 0.15, 0.1]. Minimized truncation tax at 768d.

Update README.md

Upgrade to V2 via Multi-Task Learning. Test Score: 0.8498 (Beat V1: 0.8483)

Upgrade to V2 via Multi-Task Learning

Update README.md

Add exported onnx model 'model_qint8_avx512_vnni.onnx' (#2)

Add exported onnx model 'model_qint8_avx512_vnni.onnx' (#1)

Update README.md

Upload 11 files

Update README.md

Update README.md

Upload 11 files

initial commit