Stars
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Fully open reproduction of DeepSeek-R1
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
verl: Volcano Engine Reinforcement Learning for LLMs
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
Creation of annotated datasets from scratch using Generative AI and Foundation Computer Vision models
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
mllm-npu: training multimodal large language models on Ascend NPUs
unify-easy-llm（ULM）旨在打造一个简易的一键式大模型训练工具，支持Nvidia GPU、Ascend NPU等不同硬件以及常用的大模型。
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
deepspeedai / Megatron-DeepSpeed
Forked from NVIDIA/Megatron-LMOngoing research training transformer language models at scale, including: BERT & GPT-2
Train transformer language models with reinforcement learning.
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Pytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”
[NeurIPS 2022 Spotlight] A Unified Model for Multi-class Anomaly Detection
Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.
Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline