Overview: Tinker Cookbook

The next sections provide a variety of guides for how to use the Tinker API for research and applications.

We expect people to use Tinker in a few different ways:

1. You want to define datasets and environments and plug them into existing training code from the Tinker Cookbook.
2. You want to write your own training loops from scratch, starting with the basics.
3. You want to understand the classes and other concepts in Tinker Cookbook so you can extend them to add new functionality.

Different parts of the docs will be tailored to these different approaches.

We'll start with a couple of general pages that'll be relevant to almost all of the use cases:

• Rendering to Tokens -- how we convert from a conversation data structure to a list of tokens (a.k.a. chat templates).
• LoRA Primer -- basic background of LoRA, and how to choose hyperparameters. For most fine-tuning applications, LoRA will give results that are roughly the same as full fine-tuning, however, you need to use different learning rates.