A2Summ

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, and more.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

?? Build multimodal AI applications with cloud-native stack

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).

SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.

The world’s first real-time, distributed, cloud-edge collaborative multimodal AI Agent Framework that simultaneously supports C/C++/Go/Python/JS/TS