Update README.md

README.md

@@ -14,7 +14,9 @@ This repository hosts the optimized versions of [gpt-oss-20b](https://huggingfac
 
 Optimized models are published here in [ONNX](https://onnx.ai) format to run with [ONNX Runtime](https://onnxruntime.ai) on CUDA GPU devices, with the precision best suited to this target.
 
-To easily get started with the model, you can use Foundry Local. See instructions [here](https://review.learn.microsoft.com/en-us/azure/ai-foundry/foundry-local/how-to/how-to-compile-hugging-face-models?branch=main&tabs=Bash).
+To easily get started with the model, you can use [Foundry Local](). See instructions [here](https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-local/get-started#run-the-latest-openai-open-source-model).
+
+You can also build [ONNX Runtime GenAI](https://onnxruntime.ai/docs/genai/) from source to get the latest changes and run the model. See instructions [here](https://onnxruntime.ai/docs/genai/howto/build-from-source.html) for building from source. You can then run the inference example [here](https://github.com/microsoft/onnxruntime-genai/blob/main/examples/python/model-chat.py).
 
 ## ONNX Models 
 The optimized configuration we have added is ONNX model for CUDA GPU using int4 kquant quantization with mixed precision and block size 32.