Guide for contributing to the tinker-cookbook repo — development setup, code style, type checking, PR process, and design conventions. Use when the user asks about how to contribute, set up the dev environment, code style, or project conventions.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Guide for developing and contributing to tinker-cookbook.
Read CONTRIBUTING.md for the full guide.
git clone https://github.com/thinking-machines-lab/tinker-cookbook.git
cd tinker-cookbook
uv sync --extra dev
pre-commit install
This installs dev dependencies and registers pre-commit hooks (ruff formatting/linting).
uv run ruff check tinker_cookbook/
uv run ruff format tinker_cookbook/
uv run pyright tinker_cookbook/
Any and type: ignore — prefer castingConfig objects build runtime objects:
SupervisedDatasetBuilder → SupervisedDatasetRLDatasetBuilder → RLDatasetEnvGroupBuilder → group of Env objectsConfig objects use @chz.chz decorator. They have a __call__ method that builds the runtime object.
@chz.chz dataclasses, serializable, lightweighttinker_cookbook/<module>/train.py — Main training loop with detailed Config (not CLI-constructable)tinker_cookbook/recipes/<name>/train.py — Launch script with CLIConfig from command linesl_loop.py) uses sync for simplicityEnv objects are single-use (no reset)EnvGroupBuilder, not individual EnvsSubscript suffixes on variable names:
_P = problems, _G = groups, _T = tokens, _D = datumstokens_P_G_T[p][g][t] = token t of group g of problem ptokens_PG_T = problems and groups merged into one dimensionmainpre-commit run --all-filesCI runs pre-commit, pyright, and pytest on every PR.
See the /ci skill for full testing details.
# Unit tests (no API key needed)
uv run pytest tinker_cookbook/
# Integration tests (requires TINKER_API_KEY)
uv run pytest tests/
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Guide for checkpointing — saving, loading, and resuming training with CheckpointRecord. Use when the user asks about saving weights, resuming training, checkpoint management, or the checkpoint lifecycle.
中文简介正在准备中。当前显示原文说明。
Guide for testing conventions and CI pipelines — unit tests, integration smoke tests, pytest markers, and GitHub Actions workflows. Use when the user asks about testing, CI, running tests, or adding tests for a recipe.
中文简介正在准备中。当前显示原文说明。
Guide for using completers — TokenCompleter and MessageCompleter for text generation during RL rollouts and evaluation. Use when the user asks about generating text, completing messages, or using completers in RL environments.
中文简介正在准备中。当前显示原文说明。
Guide for dataset construction — SupervisedDatasetBuilder, RLDatasetBuilder, ChatDatasetBuilder, and custom dataset creation from JSONL, HuggingFace, or conversation data. Use when the user asks about datasets, data loading, data preparation, or custom data formats.
中文简介正在准备中。当前显示原文说明。
Set up and run knowledge distillation (on-policy, off-policy, or multi-teacher) from a teacher model to a student model using the Tinker API. Use when the user wants to distill knowledge, compress models, or train a student from a teacher.
中文简介正在准备中。当前显示原文说明。
Set up and run Direct Preference Optimization (DPO) training on preference datasets using the Tinker API. Use when the user wants to train with preference data, chosen/rejected pairs, or DPO.
中文简介正在准备中。当前显示原文说明。