# Blip-2 as a classification model
**URL:**
**Author:**  [@atomwalk12](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fatomwalk12)%5C
**Post date:** [August 21, 2024, 6:29pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fblip-2-as-a-classification-model%2F103383%2F1 "2024-08-21T18:29:31Z")
I was wondering is it even possible to use the Blip-2 model (Blip2ForConditionalGeneration) for classification-like tasks. I have not been able to find any thorough information on how to use this model using a classification head.
Also, if the answer is yes, then which features should be extracted to train the classifier on. I can think of two possibilities:
1. Use the last\_hidden\_layer from the q-former and combine these features with the last\_hidden\_layer of the vision model; or
2. Use the pooled output of the q-former.
I feel like this is an interesting topic, which unfortunately was not able to find much information about.
Any related tips would be really appreciated. Thanks!
---
**Author:**  [@AmlEsmail](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAmlEsmail)%5C
**Post date:** [November 23, 2025, 12:53am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fblip-2-as-a-classification-model%2F103383%2F2 "2025-11-23T00:53:11Z")
Hey, any luck on that?
I use it for classifying if an image matches a text or not, I just take the embeddings from image and text, find the cosine similarity then use a threshold to see if it’s matching or not
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [November 23, 2025, 5:46am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fblip-2-as-a-classification-model%2F103383%2F3 "2025-11-23T05:46:44Z")
BLIP-2 can also handle this, but [for the purpose of completing this task, there seems to be no need to limit it to BLIP-2](https://huggingface.co/datasets/John6666/forum2/blob/main/blip2_classification_1.md) today…