BiT-M Feature Vector
BiT-M Feature Vector is Google's image to text model. Big Transfer (BiT-M) vision model that produces dense feature vector embeddings for downstream image classification and transfer learning.
google-bit-featurevector |
| Image to Text |
| Active |
| Google |
| 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 |
|---|---|---|---|---|---|
| BiT-M Feature Vector | — | — | — | — | Current |
| BiT-M Classification | — | — | — | — | Available |
| BiT-M R50x3 | — | — | — | — | Available |
| BiT-M R50x3 ImageNet-21k | — | — | — | — | Available |
| BiT-M R50x3 ImageNet-21k | — | — | — | — | Available |
| BiT-S R101x1 | — | — | — | — | Available |
| BiT-S R101x1 Feature Vector | — | — | — | — | Available |
| BiT-S R101x3 | — | — | — | — | Available |
| BiT-S R101x3 Feature Vector | — | — | — | — | Available |
| BiT-S R152x4 | — | — | — | — | Available |
| BiT-S R50x1 | — | — | — | — | Available |