Post-training with Tinker
Tinker Cookbook is a collection of libraries and examples for fine-tuning language models through the Tinker training service, which handles distributed training behind an API. It is used by researchers and developers for language-model post-training and experimentation, with examples built around common fine-tuning tasks. The catalogue entries provide agent workflows and integrations for using the cookbook.
This repository also configures its own agents. See what tinker-cookbook tells them →
thinking-machines-lab/tinker-cookbook
Plugin Claude Code
Bundles 4 skills · 506 tokens together
Skills for fine-tuning language models with the Tinker API — research, debugging, and more.