Train transformer language models with reinforcement learning.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

[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

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Hackable and optimized Transformers building blocks, supporting a composable construction.

粵文語料篩選器 Cantonese text filter

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.

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

Official repository for ICCV 2023: Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class

A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.

Grounded Language-Image Pre-training

LAVIS - A One-stop Library for Language-Vision Intelligence

The official GitHub page for the survey paper "A Survey of Large Language Models".

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

Refine high-quality datasets and visual AI models

VisionLLM Series

[CVPR 2023] Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

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

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"