Starred repositories
[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model…
Data annotation toolbox supports image, audio and video data.
The Open-Source Data Annotation Platform
A modular graph-based Retrieval-Augmented Generation (RAG) system
[ECCV 2024 Oral] EDTalk - Official PyTorch Implementation
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。
SGLang is a fast serving framework for large language models and vision language models.
Code and example data for the paper: Rule Based Rewards for Language Model Safety
🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Azure / DeepSeek), Knowledge Base (file upload / knowledge manageme…
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
A generative speech model for daily dialogue.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.
Instant voice cloning by MIT and MyShell.
[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
RewardBench: the first evaluation tool for reward models.
[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Mixture-of-Experts for Large Vision-Language Models
Leaked GPTs Prompts Bypass the 25 message limit or to try out GPTs without a Plus subscription.