### This is a Package Competition This is the first competition that requires submissions to be [Kaggle Packages](https://www.kaggle.com/docs/packages). This new feature expands on experimental functionality introduced in a few recent competitions and allows you to: * Submit models defined with a `predict()` function for scoring * Create simpler solutions as Kaggle’s scoring infrastructure will handle the test set iteration * Share and discover solutions that are reusable as installable inferenceable models with defined dependencies using `kagglehub` When you submit your Package to this competition, we will install your Notebook's Package in a Container with your Notebook's Accelerator and Environment settings, with Internet disabled. Our scoring system will call your Model to run inference over the hidden test set and determine your score. To learn how to create a Kaggle Package to submit to this competition, fork one of our two starter notebooks ([basic](https://www.kaggle.com/code/dster/drawing-with-llms-starter-notebook) or [advanced](https://www.kaggle.com/code/ryanholbrook/drawing-with-llms-starter-notebook)) and check out our [documentation](https://www.kaggle.com/docs/packages). ### Package Competitions are Code Competitions Submissions to this competition must be made through Notebooks. In order for the "Submit" button to be active after a commit, the following conditions must be met: - CPU Notebook <= 9 hours run-time - GPU Notebook <= 9 hours run-time - Internet access disabled - Freely & publicly available external data is allowed, including pre-trained models Please see the [Code Competition FAQ](https://www.kaggle.com/docs/competitions#notebooks-only-FAQ) for more information on how to submit. And review the [code debugging doc](https://www.kaggle.com/code-competition-debugging) if you are encountering submission errors.