Skip to content

PaLI-X

Google ResearchImage captioningVideo descriptionCharacter recognition (OCR)Visual question answering

The PaLI-X model is a image captioning model from Google Research with 55000000000.0 parameters.

About PaLI-X

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-ra

Details

Provider
Google Research
Task
Image captioning,Video description,Character recognition (OCR),Visual question answering
Parameters
55000000000.0
Released
2023-05-29
Open weights
No
View model source

Explore

FAQ