Downloads · 30 days
5
9% of all-time downloads
vicreg-resnet50-celeba
dlf-ssl/vicreg-resnet50-celeba
vicreg-resnet50-celeba is a machine learning model from dlf-ssl. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
Model trained using vicreg architecture.
All-time downloads
53
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors639 MB · 100%
At a glance
- Library
- pytorch
- Access
- Public
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026
- SHA
- 8aaad82f
Model card
From the Hugging Face model README
vicreg-resnet50-celeba
Model trained using vicreg architecture.
Model Details
- Method: vicreg
- Backbone: resnet50
- Dataset: celeba
Selected checkpoints
0, 10, 100, 500, 1000
Loading Safetensors
Reconstruct the model in your codebase, then load:
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
# This will automatically download just the epoch 100 file and cache it locally
ckpt_path = hf_hub_download(
repo_id="dlf-ssl/vicreg-resnet50-celeba",
filename="checkpoints/epoch_0100/model.safetensors"
)
state_dict = load_file(ckpt_path)
model.load_state_dict(state_dict, strict=False)
model.eval()
- Library
- pytorch
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026