Replies: 1 comment
-
This is indeed a multimodal embedding model but do note that this is trained for primarily retrieval purposes. I am not sure how this will perform for general embedding tasks but it is an interesting architecture nonetheless. Here's something I quickly threw together: ![]() The paper does a great job of explaining it in further detail. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello! I am reading the section "Multimodal Embedding Models" in Chapter 9.
May I ask is colpali/colqwen also "Multimodal Embedding Model"?
https://huggingface.co/vidore/colpali-v1.3
Beta Was this translation helpful? Give feedback.
All reactions