Salesforce / instructblip-flan-t5-xl

Vision4B15.1K30Updated Feb 3, 2025

Downloads

15.1K

Likes

30

Last updated

Feb 3, 2025

License

mit

InstructBLIP model using Flan-T5-xl as language model. InstructBLIP was introduced in the paper InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning by Dai et al.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • pytorch
  • instructblip
  • image-text-to-text
  • vision
  • image-captioning

Technical specifications

Parameters4B
Librarytransformers
Languagesen
Licensemit