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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
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/
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.