ONNX (compiled) version of the model
#18
by
Xenova
- opened
Hi there! I spent a couple of days working on an optimized ONNX export for the model, which I have uploaded to https://huggingface.co/onnx-community/Youtu-LLM-2B-ONNX. This should help with cross-platform and on-device deployment for anyone running in an environment that supports ONNXRuntime!