huggingface-models

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

This Next.js application generates videos based on client-provided queries. It is designed as a SaaS platform, allowing users to easily create engaging video content for various purposes such as marketing, education, or social media. The app leverages cutting-edge technologies to provide a smooth user experience and high-quality video output

A gopeed-extension for downloading models and datasets from huggingface, hf-mirror and modelscope. Huggingface download

Object storage for the AI age

[CVPR 2025] HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

Mount remote repositories, models and datasets managed by Git LFS instantly.

huggingface-go : 高速下载 huggingface 的模型和数据集

Upload & Merge CSV or JSON Data with Images to Notion Database

Easy text classification for everyone : Bert based models via Huggingface transformers (KR / EN)

Multimodal-OCR is an experimental, high-performance visual reasoning and optical character recognition suite designed to accurately extract text, analyze visual content, and parse complex document structures. Built upon a diverse ecosystem of cutting-edge vision-language models.

Mono repo with support for HuggingFace packages including diffusers, embeddings, transformers and grouding dino

ScaleDP is an Open-Source extension of Apache Spark for Document Processing

ORLA is a web application that transforms text prompts into detailed 3D models using advanced AI technologies. With an intuitive interface and powerful backend, ORLA enables users to generate high-quality 3D assets quickly and easily.

A 5-way embedding model for text, audio, image, video, and 3D point clouds.

Neuromorphic Bird Classifier Desktop App (NeuroBCDA) bundled with Live Event Camera Simulator

Qwen3.8-27B-Object-Detection is a high-capacity vision-language grounding, object detection, and spatial path-mapping workspace powered by the Qwen/Qwen3.8-27B model. The pipeline utilizes native Flash Attention 2 kernels (kernels-community/flash-attn2@v3) to accelerate token decoding and high-resolution visual processing dedicated tasks.

Multimodal Document Processing RAG with LangChain

Huggingface Backup - Jupyter, Colab and Python Script

Simple Generative AI enabled Streamlit web application that converts speech to-image.