CaiT XXS24 224
CaiT XXS24 224 is Meta's image to text model. An extra-extra-small CaiT image classification model with 24 layers and 224px resolution for highly efficient visual inference.
Meta's image to text model. An extra-extra-small CaiT image classification model with 24 layers and 224px resolution for highly efficient visual inference.meta-cait-xxs24-224 |
| Image to Text |
| Active |
| Meta |
| Image |
| Text |
Capabilities
Input1/5
·
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| CaiT XXS24 224 | — | — | — | — | Current |
| CaiT M36 384 | — | — | — | — | Available |
| CaiT M48 448 | — | — | — | — | Available |
| CaiT S 24 224 | — | — | — | — | Available |
| CaiT S24 384 | — | — | — | — | Available |
| CaiT S36 384 | — | — | — | — | Available |
| CaiT XS24 384 | — | — | — | — | Available |
| CaiT XXS24 384 | — | — | — | — | Available |
| CaiT XXS36 224 | — | — | — | — | Available |
| CaiT XXS36 384 | — | — | — | — | Available |