Fast Multimodal LLM on Mobile Devices

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

A toolbox of ocr models and algorithms based on MindSpore

Apache Spark - A unified analytics engine for large-scale data processing

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

Remote shuffle service for Apache Spark to store shuffle data on remote servers.

The world's fastest open query engine for sub-second analytics both on and off the data lakehouse. With the flexibility to support nearly any scenario, StarRocks provides best-in-class performance …

one for all, Optimal generator with No Exception

📚 极客时间电子书

嵌入式软件开发文档整理

Emu Series: Generative Multimodal Models from BAAI

A rapid prompt app development framework based on GPT

Complex LLM Workflows from Simple JSON.

Focus on creative things about LLM-Powered Multi-Agents.

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

Build agents which are controlled by LLMs

The no-code platform for building custom LLM Agents

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Implementation of DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

A toolbox of OCR models, algorithms, and pipelines based on MindSpore

Awesome-LLM: a curated list of Large Language Model

Easy-to-use and high-performance NLP and LLM framework based on MindSpore, compatible with models and datasets of 🤗Huggingface.