tinker

name	tinker
description	Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, multimodal models including Thinking Machines' Inkling (vision, audio, thinking effort), and both high-level Cookbook patterns and low-level API usage.

Tinker API - LLM Fine-Tuning

Overview

Tinker is a training API for large language models from Thinking Machines Lab. It provides:

• Supervised Fine-Tuning (SFT): Train models on instruction/completion pairs
• Reinforcement Learning (RL): PPO and policy gradient losses; cookbook patterns include GRPO-like group rollouts/advantage centering
• Multimodal Models: vision via Qwen3.5/3.6 and Kimi K2.x; vision + audio via Inkling
• Inkling: Thinking Machines' own open-weights MoE model (975B/41B active, released July 2026) with text/image/audio inputs and tunable thinking effort
• LoRA Training: Efficient parameter-efficient fine-tuning

Two abstraction levels:

• Tinker Cookbook: High-level patterns with automatic training loops
• Low-Level API: Manual control for custom training logic

Quick Reference

Topic	Reference
Setup & Core Concepts	Getting Started
API Classes & Types	API Reference
Supervised Learning	Supervised Learning
RL Training	Reinforcement Learning