Base on https://huggingface.co/Qwen/Qwen2-0.5B-Instruct
Convert to onnx model using https://github.com/microsoft/onnxruntime-genai
Using command: python src/python/py/models/builder.py -m Qwen/Qwen2-0.5B-Instruct -o path-to-onnx-model -p int4 -e dml
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support