Instructions to use nyu-visionx/webssl300m_decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyu-visionx/webssl300m_decoder with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-image", model="nyu-visionx/webssl300m_decoder")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForPreTraining processor = AutoImageProcessor.from_pretrained("nyu-visionx/webssl300m_decoder") model = AutoModelForPreTraining.from_pretrained("nyu-visionx/webssl300m_decoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add model card for Scale-RAE
Verified signatureHi, I'm Niels from the Hugging Face community team. This PR adds a model card for the Scale-RAE artifact, including: - Metadata for `library_name`, `license`, and `pipeline_tag`. - Links to the research paper, project page, and official GitHub repository. - A brief description of the model based on the paper. - The BibTeX citation for the work.5422b55
-
Fix config.json: Change hidden_size from 1152 to 1024 to match WebSSL DINO encoder output dimension
Verified signature906f602
-
Upload config.json with huggingface_hub
Verified signature822cf65
-
Upload model.pt with huggingface_hub
Verified signaturec75629d -
initial commit
Verified signature4db152a