Tinker Cookbook is an open-source framework for fine-tuning large language models, supporting supervised learning, reinforcement learning, and parameter-efficient techniques like LoRA adapters. It provides a complete pipeline for aligning models with human preferences through multi-stage RLHF workflows, from supervised fine-tuning through preference optimization to reinforcement learning. The framework distinguishes itself through recipe-based training orchestration, where fine-tuning workflows are defined as composable recipe files that chain data loading, model configuration, and training l
Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip
Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo
AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p
Acest proiect este un framework de aliniere și o suită de pipeline-uri pentru antrenarea modelelor de limbaj folosind fine-tuning supervizat și optimizarea preferințelor. Oferă instrumente pentru executarea antrenării distribuite la scară largă pe mai multe GPU-uri și noduri de calcul, alături de un sistem pentru măsurarea utilității modelului și a calității dialogului prin benchmark-uri single-turn și multi-turn.
Principalele funcționalități ale huggingface/alignment-handbook sunt: Preference Alignment, Reward Modeling, Direct Preference Optimization, Distributed Training Configurations, Large Scale Training Suites, Distributed Training, Alignment Frameworks, Multi-Stage Pipelines.
Alternativele open-source pentru huggingface/alignment-handbook includ: thinking-machines-lab/tinker-cookbook — Tinker Cookbook is an open-source framework for fine-tuning large language models, supporting supervised learning,… meta-pytorch/torchtune — Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a… pytorch/torchtune — Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a… openrlhf/openrlhf — OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across… inclusionai/areal — AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a… allenai/open-instruct — Open-Instruct is a distributed training and instruction tuning framework for large language models. It functions as a…