xuhzyy

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

parler-tts

Inference and training library for high-quality TTS models.

pipecat

Open Source framework for voice and multimodal conversational AI

RealtimeSTT

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

RealtimeTTS

Converts text to speech in realtime

ChatTTS

ChatTTS is a generative speech model for daily dialogue.

HunyuanDiT

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

sig

Interactive grep (for streaming)

surya

OCR, layout analysis, reading order, line detection in 90+ languages

T-Rex

API for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Grounding-DINO-1.5-API

API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

yolov10

YOLOv10: Real-Time End-to-End Object Detection

cpp-httplib

A C++ header-only HTTP/HTTPS server and client library

Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

AlphaPose

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

agentscope

Start building LLM-empowered multi-agent applications in an easier way.

RepViT

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

Segment-Everything-Everywhere-All-At-Once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

GroundingDINO

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

chroma

the AI-native open-source embedding database

modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

OpenAGI

OpenAGI: When LLM Meets Domain Experts

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

AgentLite

Qwen-Agent

Agent framework and applications built upon Qwen1.5 & Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.