🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV github.com/open-mmlab/mmg…

K-Net addresses instance/semantic/panoptic segmentation in a unified, simple, and effective framework. SOTA on COCO Panoptic Segmentation with 55.2% PQ. Our NeurIPS'21 paper: arxiv.org/abs/2106.14855 Project Page: mmlab-ntu.com/project/knet/ Code: github.com/ZwwWayne/K-Net

NeurIPS poster presentation of K-Net at 00:30 PST. See you guys there! #NeurIPS2021 NeurIPS Conference

✨Our new SUPERMAN - MMDeploy! github.com/open-mmlab/mmd… This powerful deployment toolkit bridges the gap between R&D and applications. - Compatible with OpenMMLab codebases and PyTorch - Support multiple inference backends and hardwares Try it and free yourself from dirty work!

😍Excited to share the good news with everyone that MMDetection just hits 20k stars on GitHub. 🤗We appreciate all contributions from the community to MMDetection. github.com/open-mmlab/mmd…

The MMLab@NTU team has a total of 18 papers accepted to ECCV 2022 🥳 We will release our papers and code. Stay tuned! mmlab-ntu.com/publication_ye…

Thrilled to release MMYOLO, a new member of the MMDet/OpenMMLab family, which is mainly contributed by the community！

A small step towards the goal of MMDet to provide complete and smooth functionality and benchmark for the computer vision community

#AAAI23 🥳Wenwei Zhang from MMLab will introduce one of most popular toolboxes in #objectdetection -- MMDetection. ☺️He will show how to conduct research projects related to object detection efficiently with this toolbox. 😘github.com/open-mmlab/mmd…

🔥Exploring new frontiers with MMGPT! -------------------------------------------------- 👨‍💼Support various vision and language instruction data 🚀Parameter efficient fine-tuning with LoRA 🤖Tuning vision and language at the same time, complement each other github.com/open-mmlab/Mul…

OpenMMLab and OpenDataLab are organizing the #CVPR2023 tutorials in the East 12 room now! Please come if you want to boost your computer vision research with OpenMMLab toolboxes and OpenDataLab data platforms! #PyTorch

Thrilled to release Lagent! A new framework that allows you to quickly build LLM-based agent! Tired of the heavy and complex langchain? Try Lagent! github.com/InternLM/lagent

Try Internlm2-Chat models and you might get more surprise😎

How to let #LLM acquire the Agentic Capability? #Agent-FLAN finds: - Eliciting the foundational capability (e.g., #reasoning) is more important - Using chat data is more effective without side effects Project page：internlm.github.io/Agent-FLAN/ Try it at：huggingface.co/internlm/Agent…

Would this be one of the best local LLM under 10B? Or best small server side model with up to 1M context length? InternLM-2.5 7B family just dropped on Hugging Face ! huggingface.co/collections/in… License: Free commercial usage upon request with blanket approval.

🥳Still waiting for #SearchGPT? Let's try MindSearch at github.com/InternLM/minds… MindSearch mimics human minds in complex web search by a multi-agent framework, which is fully open-sourced now! You can build it locally with API models like GPT-4o or open-source model InternLM2.5!

What's the limit of reinforcement learning and 7B LLM on MATH-500? The answer is 94.0 pass@1 accuracy! The method is OREAL, a new #RL method. Check it at huggingface.co/papers/2502.06… github.com/InternLM/OREAL

🥳Thrill to release the full RL training code of #OREAL! 😊Now you can fully reproduce the results of OREAL-7B/32B. Using #DeepSeek-R1-Distill-Qwen-32B, you can further obtain a model has 95.6 on MATH-500! 🤗Code: github.com/InternLM/OREAL 🤗Based on: github.com/InternLM/xtuner