Google logo

EfficientNet V2 ImageNet-21k FT1k L

EfficientNet V2 ImageNet-21k FT1k L is Google's image to text model. A large EfficientNet V2 model pretrained on ImageNet-21k and fine-tuned on ImageNet-1k, designed for high-accuracy image classification with extensive compound scaling.
Specifications
Canonical IDgoogle-efficientnet-2-imagenet21k-ft1k-l
TypeImage to Text
StatusActive
CreatorGoogleGoogle
Input ModalitiesImage
Output ModalitiesText

Capabilities

Input1/5
TextΒ·
Imageβœ“
AudioΒ·
VideoΒ·
PDFΒ·
Output1/5
Textβœ“
ImageΒ·
AudioΒ·
VideoΒ·
EmbeddingΒ·
Capabilities0/13
ReasoningΒ·
Adaptive ReasoningΒ·
Function CallingΒ·
Parallel Function CallingΒ·
Structured OutputsΒ·
Native JSON SchemaΒ·
Web SearchΒ·
URL ContextΒ·
Computer UseΒ·
Code ExecutionΒ·
File SearchΒ·
Prompt CachingΒ·
Assistant PrefillΒ·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
EfficientNet V2 ImageNet-21k FT1k Lβ€”β€”β€”β€”Current
EfficientNet V2 ImageNet-1k B0β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-1k B1β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-1k B2β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-1k B3β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-1k Largeβ€”β€”β€”β€”Available
EfficientNet V2 ImageNet-1k Mediumβ€”β€”β€”β€”Available
EfficientNet V2 ImageNet-21k B0β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-21k B1β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-21k B2β€”β€”β€”β€”Available
EfficientNet V2 ImageNet-21k B3β€”β€”β€”β€”Available

Model IDs