A generative speech model for daily dialogue.

OpenMMLab Detection Toolbox and Benchmark

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Official release of InternLM2.5 base and chat models. 1M context support

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

A Comprehensive Toolkit for High-Quality PDF Content Extraction

OpenMMLab Computer Vision Foundation

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

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

The LLM Evaluation Framework

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

A lightweight framework for building LLM-based agents

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Open-source evaluation toolkit of large vision-language models (LVLMs), support 160+ VLMs, 50+ benchmarks

[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画

Data annotation toolbox supports image, audio and video data.

GRUtopia: Dream General Robots in a City at Scale

SDK of OpenDataLab - https://opendatalab.org.cn

SoccerDB: A Large-Scale Database for Comprehensive Video Understanding