Statements (23)
Predicate | Object |
---|---|
gptkbp:instanceOf |
multimodal AI model
|
gptkbp:architecture |
vision-language model
|
gptkbp:basedOn |
gptkb:Vicuna
BLIP-2 |
gptkbp:developedBy |
gptkb:King_Abdullah_University_of_Science_and_Technology
|
https://www.w3.org/2000/01/rdf-schema#label |
MiniGPT-4
|
gptkbp:input |
gptkb:illustrator
gptkb:text |
gptkbp:language |
English
|
gptkbp:license |
Apache 2.0
|
gptkbp:memiliki_tugas |
image captioning
visual question answering image description generation |
gptkbp:notableFor |
demonstrating strong multimodal capabilities
efficient training with limited resources |
gptkbp:openSource |
true
|
gptkbp:output |
gptkb:text
|
gptkbp:releaseDate |
April 2023
|
gptkbp:repository |
https://github.com/Vision-CAIR/MiniGPT-4
|
gptkbp:uses |
large language model
pre-trained vision encoder |
gptkbp:bfsParent |
gptkb:MiniGPT
|
gptkbp:bfsLayer |
6
|