GitHub - JayZeeDesign/claude-code-proxy: Run Claude Code on OpenAI models
Run Claude Code on OpenAI models. Contribute to JayZeeDesign/claude-code-proxy development by creating an account on GitHub.
skills/skills/tinker/SKILL.md at main · sundial-org/skills
github.comSaved January 10, 2026
Summary
Tinker is a training API for fine-tuning large language models from Thinking Machines Lab, supporting supervised fine-tuning, reinforcement learning, LoRA, and vision-language models.
It offers both a high-level Cookbook with automatic training loops and a low-level API for manual control, with reference guides for setup, SFT, RL, loss functions, rendering, models/LoRA, and recipes. Installation uses pip packages `tinker` and `tinker-cookbook`, and example code demonstrates creating a LoRA training client, preparing tokenized data, running forward/backward + optimizer steps, and sampling from the trained model.
