This is a fantastic resource for developers interested in experimenting with multiple LLMs without the overhead of setting up separate environments. However, as @imjonse mentioned, it seems that the notebook calls out to proprietary APIs, meaning the heavy lifting isn't happening entirely within Colab. Can anyone shed light on which parts are executed externally versus locally? Also, are there open-source alternatives that allow for fully local fine-tuning and deployment within Colab or other accessible platforms?