Pass IndexThe State of AISign in

blip-vqa-base

Model card for BLIP trained on visual question answering- base architecture (with ViT base backbone).

text + image → text · made by Salesforce

Sold by

Nobody in the catalogue publishes a price for this yet.

About

blip-vqa-base — a text model from Salesforce.

It takes text and images and returns text. It was published in December 2022. The catalogue files it under chat. Its weights are published under BSD-3-CLAUSE, so you may run it on your own machine, or buy it from whoever serves it cheapest.

Every current figure

Maker
Salesforce
Register
model
Takes
text + image
Returns
text
Published
December 2022
Parameters
385 million · read from its own weights
Licence
bsd-3-clause

Known as 1 name

Salesforce/blip-vqa-base