Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Scalable toolkit for efficient model reinforcement

Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.

Wan: Open and Advanced Large-Scale Video Generative Models

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

slime is an LLM post-training framework for RL Scaling.

Repo of Jinx: Unlimited LLMs for Probing Alignment Failures

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.

Kimi K2 is the large language model series developed by Moonshot AI team

Nano vLLM

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

This is the repository for the Tool Learning survey.

A simple, secure MCP-to-OpenAPI proxy server

The official Python SDK for Model Context Protocol servers and clients

🚀 Efficient implementations for emerging model architectures

Ongoing research training transformer models at scale

Expert Parallelism Load Balancer

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient Multi-head Latent Attention Kernels

Democratizing Reinforcement Learning for LLMs

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Development repository for the Triton language and compiler

Vane is an AI-powered answering engine.

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Robust Python parser for W&B's `.wandb` binary structured log format.