colpali icon indicating copy to clipboard operation
colpali copied to clipboard

Why not remove describe text embedding in image_embeddings output

Open k1eNdn opened this issue 1 year ago • 0 comments

I am using the vidore/colqwen2-v0.1 model to embed documents and queries. In the code, I noticed that you removed pixel_values during the query processing, but you didn't remove the described embedding during the image processing. Does this affect the results of late interaction search?

k1eNdn avatar Oct 12 '24 05:10 k1eNdn