Upload config.json with huggingface_hub

Upload model.safetensors with huggingface_hub

Sync yolo-coder-1.5b-int8.onnx to fixed fp32-clean model

Comprehensive fp16→fp32: fix 311 initializers + 228 Cast nodes + 56 Constant tensors + 1464 type annotations

Add yolo-coder-1.5b-int8.onnx alias

Fix Cast-to-fp16 nodes → fp32 for ONNX Runtime Web compatibility

Fix fp16 scale tensors → float32 for ONNX Runtime Web compatibility

Add onnx/model_quantized.onnx (Transformers.js v3 naming convention)

Add onnx/decoder_model_merged_quantized.onnx for Transformers.js

Add chat_template.jinja

Add tokenizer_config.json

Add tokenizer.json

Add ONNX (fp16 + int8) export of YOLO-Coder-1.5B for Transformers.js

initial commit