• multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.

Qwen2-Audio is an open multimodal model that natively accepts audio and text and returns text, enabling voice chat and audio analysis without stitching together a separate speech-to-text pipeline. Useful if you want an open-weights alternative to closed audio-in models for building voice-driven or audio-understanding features.

• articleChinese CLIP: Contrastive Vision-Language Pretraining in Chinese
• articleOFASys: Enabling Multitask Learning with One Line of Code!
• articleQwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters
• articleGeneralizing an LLM from 8k to 1M Context using Qwen-Agent

• articleQwen2.5 Omni: See, Hear, Talk, Write, Do It All!Qwen Team
• articleQwen2.5 VL! Qwen2.5 VL! Qwen2.5 VL!Qwen Team
• articleQwen2-VL: To See the World More ClearlyQwen Team

Checking sign-in…

Loading comments…