An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

🔍 🐍 Like pstack but for Python!

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / veRL/ Swift / Ultra…

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…

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

verl: Volcano Engine Reinforcement Learning for LLMs

Community maintained hardware plugin for vLLM on Ascend

Fully open reproduction of DeepSeek-R1

Research on Tabular Deep Learning: Papers & Packages

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

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

Jupyter notebooks for the Natural Language Processing with Transformers book

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Transformer related optimization, including BERT, GPT

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

基于ChatGLM-6B + LoRA的Fintune方案

The AI Code Editor

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Instruct-tune LLaMA on consumer hardware

LLM inference in C/C++

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

An open-source framework for training large multimodal models.

🦜🔗 The platform for reliable agents.

LlamaIndex is the leading framework for building LLM-powered agents over your data.