Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Large-scale text embedding model

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Python tool for converting files and office documents to Markdown.

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"

verl: Volcano Engine Reinforcement Learning for LLMs

Free and Open Source, Distributed, RESTful Search Engine

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive A…

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

DeepEP: an efficient expert-parallel communication library

🤖一个基于 WeChaty 结合 DeepSeek / ChatGPT / Kimi / 讯飞等Ai服务实现的微信机器人 ，可以用来帮助你自动回复微信消息，或者管理微信群/好友，检测僵尸粉等...

FlashMLA: Efficient Multi-head Latent Attention Kernels

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Fully open reproduction of DeepSeek-R1

Fully open data curation for reasoning models

[ICLR 2025] Released code for paper "Spurious Forgetting in Continual Learning of Language Models"

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。

OCR, layout analysis, reading order, table recognition in 90+ languages

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …