QwenLM / Qwen2-VL

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Apache License 2.0
3.11k stars 189 forks source link

Can we get img/text embedding from QWEN2-VL to realize text-img retrieval? #510

Open LianghuiGuo opened 1 week ago

LianghuiGuo commented 1 week ago

How to get img/text embedding from QWEN2-VL? And can we use it to do text-img retrieval?

QVQZZZ commented 2 days ago

hi,请问你测试过图文检索/召回的效果吗?