thinking-machines-lab/tinker-cookbook

PyTorch native post-training library

Train transformer language models with reinforcement learning.

An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques

A Lightweight LLM Post-Training Library

AllenAI's post-training codebase

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

Open Source Instruction Tuning LLM Training Library 2026

Robust recipes to align language models with human and AI preferences

Scalable toolkit for efficient model reinforcement