DeiT Base Patch 16 224
DeiT Base Patch 16 224 is Meta's image to text model. A Data-efficient Image Transformer base model using 16×16 patches at 224px resolution, trained without extra data for competitive image classification.
meta-deit-base-patch16-224 |
| Image to Text |
| Active |
| Meta |
| Image |
| Text |
Capabilities
Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeiT Base Patch 16 224 | — | — | — | — | Current |
| DeiT Base Distilled Patch 16 224 | — | — | — | — | Available |
| DeiT Base Distilled Patch 16 384 | — | — | — | — | Available |
| DeiT Base Patch 16 384 | — | — | — | — | Available |
| DeiT Small Distilled Patch 16 224 | — | — | — | — | Available |
| DeiT Small Patch 16 224 | — | — | — | — | Available |
| DeiT Tiny Distilled Patch 16 224 | — | — | — | — | Available |
| DeiT Tiny Patch 16 224 | — | — | — | — | Available |