Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Ola: Pushing the Frontiers of Omni-Modal Language Model

Wan: Open and Advanced Large-Scale Video Generative Models

HumanOmni

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

GLM-4-Voice | 端到端中英语音对话模型

Large Language Model Text Generation Inference

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

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

Set-of-Mark Prompting for GPT-4V and LMMs

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

Images to inference with no labeling (use foundation models to train supervised models).

Segment Anything in High Quality [NeurIPS 2023]

ModelScope: bring the notion of Model-as-a-Service to life.

Self-Supervised Speech Pre-training and Representation Learning Toolkit

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

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

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

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

A generative speech model for daily dialogue.

[CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

An open source implementation of CLIP.