Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”

Kolors Team

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

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。

本项目用于大模型数学解题能力方面的数据集合成，模型训练及评测，相关文章记录。

眼科问诊大模型

Code release for "Segment Anything without Supervision"

Brand new TTS solution

A modular graph-based Retrieval-Augmented Generation (RAG) system

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

The Largest-scale Chinese Medical QA Dataset： with 26,000,000 question answer pairs.

✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.

LLM101n: Let's build a Storyteller

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/

SuperSonic is the next-generation BI+AI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

A generative speech model for daily dialogue.

Easiest and laziest way for building multi-agent LLMs applications.

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

FlagScale is a large model toolkit based on open-sourced projects.

The Open-Source Data Annotation Platform

YoloV8 NPU for the RK3566/68/88