Tinker Cookbook
We provide two libraries for the broader community to customize their language models: tinker and tinker-cookbook.
tinkeris a training SDK for researchers and developers to fine-tune language models. You send API requests to us and we handle the complexities of distributed training.tinker-cookbookincludes realistic examples of fine-tuning language models. It builds on the Tinker API and provides common abstractions to fine-tune language models.
Installation
- Sign up for Tinker here.
- Once you have access, create an API key from the console and export it as environment variable
TINKER_API_KEY. - Install
tinker-cookbook(includes thetinkerSDK as a dependency):# Latest stable release from PyPI uv pip install tinker-cookbook # Or install the nightly build uv pip install 'tinker-cookbook @ git+https://github.com/thinking-machines-lab/tinker-cookbook.git@nightly'
Using Inkling and Inkling-Small
Inkling is Thinking Machines Lab's model tailored for Tinker. It is a
general-purpose model that can code, reason, call tools, and process image and
audio inputs. Inkling-Small is a smaller, lower-cost model in the same family
that shares Inkling's rendering path and reasoning-effort interface. Tinker
Cookbook supports sampling and post-training both through the standalone
tml-renderers library; install it with the inkling extra, which also pulls in
the required torch>=2.10:
uv pip install 'tinker-cookbook[inkling]'
Pass model_name="thinkingmachines/Inkling" or
model_name="thinkingmachines/Inkling-Small" anywhere the cookbook accepts a
model name. The appropriate renderer and tokenizer are selected automatically for
any thinkingmachines/Inkling* model, including the :peft: long-context
variants.
Both models support controllable reasoning effort as well as multimodal audio and image inputs. See the Inkling documentation for setup and usage details, and Models & Pricing for per-model context lengths and pricing.
Tinker
Here we introduce a few Tinker primitives — the basic components to fine-tune LLMs (see the quickstart guide for more details):
import tinker
service_client = tinker.ServiceClient()
training_client = service_client.create_lora_training_client(
base_model="meta-llama/Llama-3.2-1B", rank=32,
)
training_client.forward_backward(...)
training_client.optim_step(...)
training_client.save_state(...)
training_client.load_state(...)
sampling_client = training_client.save_weights_and_get_sampling_client()
sampling_client.sample(...)
See tinker_cookbook/recipes/sl_loop.py and tinker_cookbook/recipes/rl_loop.py for minimal examples of using these primitives to fine-tune LLMs.
Tutorials
New to Tinker? The tutorials/ directory contains 20+ progressive marimo notebooks that walk through core concepts — rendering, loss functions, completers, weight management — and advanced topics such as custom RL environments, DPO, RLHF, and weight export. Run any tutorial with marimo edit tutorials/101_hello_tinker.py. See the tutorials README for the full list, or browse rendered versions on the Tinker docs site.
To download the weights of any model:
rest_client = service_client.create_rest_client()
future = rest_client.get_checkpoint_archive_url_from_tinker_path(sampling_client.model_path)
with open(f"model-checkpoint.tar.gz", "wb") as f:
f.write(future.result())
Tinker Cookbook
Besides these primitives, we also offer Tinker Cookbook (a.k.a. this repo), a library of a wide range of abstractions to help you customize training environments.
tinker_cookbook/recipes/sl_basic.py and tinker_cookbook/recipes/rl_basic.py contain minimal examples to configure supervised learning and reinforcement learning.
We also include more complete examples in the tinker_cookbook/recipes/ folder:
- Chat SFT: supervised fine-tuning on conversational datasets (e.g., Tulu3).
- Math RL: reinforcement learning for mathematical reasoning with verifiable rewards.
- Code RL: RL on competitive programming with sandboxed code execution (DeepCoder replication).
- Preference learning: DPO and a three-stage RLHF pipeline (SFT, reward model, RL).
- Distillation: on-policy and off-policy knowledge distillation with single- and multi-teacher configurations.
- Tool use: RL for retrieval-augmented generation (Search-R1 replication).
- Multi-agent: multi-agent RL with self-play and cross-play.
- Audio: SFT and RL for Inkling audio inputs, including speech recognition and speaking-style classification.
- VLM image classification: supervised training and evaluation for vision-language models.
The recipes README covers all available recipes, including Harbor RL, rubric-based grading, VLM classification, and SDFT. Each recipe includes a README.md with implementation details, launch commands, and expected results.
Evaluation (experimental)
Tinker Cookbook includes a benchmark framework for evaluating trained models:
from tinker_cookbook.eval.benchmarks import run_benchmarks, BenchmarkConfig
results = await run_benchmarks(
["gsm8k", "mmlu_pro", "ifeval"],
sampling_client, renderer,
BenchmarkConfig(save_dir="evals/step500"),
)
The framework currently supports 12 benchmarks (GSM8K, MATH-500, MMLU-Pro, MMLU-Redux, GPQA, IFEval, MBPP, C-Eval, SuperGPQA, IFBench, AIME 2025, AIME 2026) with verified scores against published results, plus experimental benchmarks such as LiveCodeBench, Terminal Bench, and SWE-bench. Benchmarks can also serve as inline training evaluators via BenchmarkEvaluator.
Note: Benchmark scores are sensitive to evaluation configuration — system prompts, max_tokens, temperature, and timeout settings can shift results significantly. We document our exact settings alongside all reported scores. This framework is under active development; feedback and contributions are welcome. See the eval README for verified scores, configuration details, and instructions for adding new benchmarks.
Documentation
For the full Tinker documentation, visit tinker-docs.thinkingmachines.ai.
Utilities
Tinker Cookbook also provides reusable building blocks:
renderers— bidirectional conversion between token sequences and structured chat messageshyperparam_utils— learning rate and hyperparameter scaling for LoRA trainingeval— benchmark framework and inline training evaluators (see Evaluation above)
Claude Code Skills
Tinker Cookbook ships with Claude Code skills that teach Claude how to use the Tinker API. Install them so Claude can help you write training code in any project:
/plugin marketplace add thinking-machines-lab/tinker-cookbook
Then install the tinker plugin from the Discover tab (/plugin → Discover). Once installed, three skills are available:
| Command | What it does |
|---|---|
/tinker:research |
Plan and run post-training experiments — SFT, RL, DPO, distillation, evaluation, hyperparameters, model selection, and more |
/tinker:debug |
Diagnose slow training, hangs, output mismatches, renderer issues, and errors |
/tinker:inkling |
Work with Inkling and Inkling-Small — thinking effort, rendering, post-training, evaluation, and multimodal input |
Skills also trigger automatically based on context — ask Claude to "set up SFT training" and it will load the right skill without a slash command. Skills update automatically when the repo is updated.
Development Setup
uv sync --extra dev
pre-commit install
This installs dev dependencies and registers pre-commit hooks that run ruff formatting and linting on every commit. CI enforces these checks on all pull requests.
Contributing
This project is built in the spirit of open science and collaborative development. We believe that the best tools emerge through community involvement and shared learning.
We welcome PR contributions after our private beta is over. If you have any feedback, please email us at tinker@thinkingmachines.ai.
Citation
If you use Tinker for your research, please cite it as:
Thinking Machines Lab, 2026. Tinker. https://thinkingmachines.ai/tinker/.
Or use this BibTeX citation:
@misc{tml2026tinker,
author = {Thinking Machines Lab},
title = {Tinker},
year = {2026},
url = {https://thinkingmachines.ai/tinker/},
}
Wheel compatibility matrix
Files in release
aiohttp
(>=3.9.0)
anyio
(>=4.0.0)
blobfile
(>=3.0.0)
chz
(>=0.4.0)
cloudpickle
(>=3.0.0)
datasets
(>=2.14.0)
huggingface-hub
(>=0.20.0)
numpy
(>=1.24.0)
pillow
(>=10.0.0)
pydantic
(>=2.0.0)
rich
(>=13.0.0)
safetensors
(>=0.4.0)
termcolor
(>=2.0.0)
tiktoken
(>=0.12.0)
tinker
(>=0.22.3)
torch
(>=2.0)
tqdm
(>=4.60.0)
transformers
(!=5.4.*,!=5.5.0,!=5.5.1,!=5.5.2,!=5.5.3,<=5.5.4,>=4.57.6)