Salesforce / blip2-opt-6.7b
Vision7.8B9.9K79Updated Feb 3, 2025
Downloads
9.9K
Likes
79
Last updated
Feb 3, 2025
License
mit
BLIP-2 model, leveraging OPT-6.7b (a large language model with 6.7 billion parameters). It was introduced in the paper BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models by Li et al. and first released in this repository.
Tasks & library
- image text to text
- transformers
Tags
- transformers
- pytorch
- blip-2
- visual-question-answering
- vision
- image-to-text
Technical specifications
Parameters7.8B
Librarytransformers
Languagesen
Licensemit