Rlhf

A hands-on curriculum and code repository that teaches modern reinforcement learning from foundational control algorithms through LLM alignment,...

This repository is the official code companion to a Manning book that teaches how to build a reasoning LLM from scratch using PyTorch, starting with...

AgentsMeetRL is a curated awesome list that catalogs open-source repositories at the intersection of LLM agents and reinforcement learning, with 240+...

An open-source textbook and code library on Reinforcement Learning from Human Feedback (RLHF) and post-training for language models, with...

ROLL is a specialized RL library designed specifically for fine-tuning large language models at scale, integrating distributed training frameworks...

OpenClaw-RL is a reinforcement learning framework that enables training personalized agents through natural language interaction, supporting...

LLaMA Factory is a unified fine-tuning framework that supports 100+ large language models and vision-language models through a zero-code CLI and web...

Distilabel is a Python framework for generating synthetic data and collecting AI feedback through scalable, research-backed pipelines. It serves...

Kiln is a comprehensive workbench for the full AI development lifecycle, combining evaluations, prompt optimization, RAG, fine-tuning, synthetic data...

Argilla is a collaboration platform for building high-quality datasets through human annotation and feedback loops, designed specifically for AI...

Transformer Lab is an open-source ML platform that provides a unified interface for training, fine-tuning, and evaluating models, with editions for...

Docta is a data-centric AI platform designed to detect and fix issues in training data across tabular, text, image, and embedding formats. It...

The Alignment Handbook provides production-ready recipes and code for aligning large language models with human and AI preferences using techniques...

InternLM is an official open-source series of large language models (InternLM, InternLM2, InternLM2.5, InternLM3) developed by Alibaba's Intern-AI...

Safe RLHF is a research framework and methodology for training language models with constrained value alignment, combining Supervised Fine-Tuning,...

Chinese-LLaMA-Alpaca-2 is a fine-tuned version of Meta's Llama-2 with extended Chinese vocabulary and capabilities, offering multiple model variants...