SORRY I WAS WRONG AT 35:31 Here, you serve the model, and then you can use the REST API. You can use `ilab model chat` to directly chat with the model and don't need to serve first. See the updated blog post: suedbroecker.net/2024/06/20/fine-tune-llm-foundation-models-with-the-instructlab-an-open-source-project-introduced-by-ibm-and-red-hat/ start at step 10.