Downloads · 30 days
28
100% of all-time downloads
granite-owl
ANGExllL/granite-owl
granite-owl is a image classification model from ANGExllL. Use it when you need a label for an image. It is set up for torchvision. The card lists the license as apache-2.0.
EfficientNetV2-L (torchvision efficientnetv2l, 1000 ImageNet classes) fine-tuned with adversarial training for the Perturb subnet (netuid 26).
All-time downloads
28
Public
Parameters
119M
476 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors476 MB · 100%
At a glance
- Task
- Image Classification
- Library
- torchvision
- License
- apache-2.0
- Access
- Public
- Created
- Sep 22, 2026
- Updated
- Sep 22, 2026
- SHA
- 7c2104af
Model card
From the Hugging Face model README
ANGExllL/granite-owl
EfficientNetV2-L (torchvision efficientnet_v2_l, 1000 ImageNet classes) fine-tuned with adversarial
training for the Perturb subnet (netuid 26).
- miner hotkey:
5DhtFUDenAuSzn3EVhjL29UFWJbT1MoUVAJ83Ft94biBy25e - on-chain hash: sha256(model.safetensors || hotkey) =
6c31ff4551345cf7f82a34cc80af6172ec1804d76c0372113ef993b71356ed24 - preprocessing:
EfficientNet_V2_L_Weights.IMAGENET1K_V1.transforms()(bicubic resize 480, center crop 480, mean = std = 0.5)
from safetensors.torch import load_file
from torchvision.models import efficientnet_v2_l
model = efficientnet_v2_l(weights=None)
model.load_state_dict(load_file("model.safetensors"))
- Task
- Image Classification
- Library
- torchvision
- License
- apache-2.0
- Created
- Sep 22, 2026
- Updated
- Sep 22, 2026