Welcome to Cooking with Granite: a community hub for building with IBM's Granite Model Family and a project of The AI Alliance.
Come check out our cookbooks and our kitchen, and you'll be cooking with Granite in no time!
The following Granite Cookbooks provide open source recipes for using the Granite models:
- Granite Snack Cookbook has introductory "Hello, World!" recipes that run quickly on small datasets.
- Granite Code Cookbook
- Granite Finance Cookbook
- Granite Legal Cookbook
- Granite Time Series Cookbook
The Granite Kitchen provides information on using Granite on several hosting platforms, finding compatible vector databases, and some utilities for notebook environments.
The Granite family of foundation models span an increasing variety of modalities, including language, code, time series, and science (e.g., materials) - with much more to come. We're building them with transparency and with focus on fulfilling rigorous enterprise requirements that are emerging for AI. If you'd like to learn more about the models themselves and how we build them, check out Granite Models.
The mission of Cooking with Granite is to work collaboratively across industries and geographies to leverage Granite to solve problems and bring value across use cases, from code generation and modernization, to forecasting and predictive maintenance, to materials discovery.
Our first goal is to build out a community kitchen for Granite, starting with cookbooks that have proven recipes to help enrich, adapt, and apply Granite models to real world applications.
For more information on Granite models:
- IBM Website for Granite: More information about the Granite family of models.
- Granite Playground: A set of “no-code” example uses of Granite models.
- GitHub: The GitHub repository with miscellaneous information and tools for the Granite models themselves.
- Hugging Face: The Granite organization in Hugging Face. You can download any of the Granite models there.
All content in these repositories including code has been provided by IBM under the associated open source software license and IBM is under no obligation to provide enhancements, updates, or support. IBM developers produced this code as an open source project (not as an IBM product), and IBM makes no assertions as to the level of quality nor security, and will not be maintaining this code going forward.