isuruwijesiri/all-MiniLM-L12-v2-code-search-512

Add quantized ONNX for Transformers.js

Add ONNX export for optimized inference

Update README.md

Update README.md

v1.0: CodeSearchNet fine-tune (1,294,017 samples, 3 epochs, 91.0% Acc@1)

initial commit