Instructions to use ciderlab/siglip2-design-discriminator-backbone with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ciderlab/siglip2-design-discriminator-backbone with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="ciderlab/siglip2-design-discriminator-backbone") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("ciderlab/siglip2-design-discriminator-backbone") model = AutoModelForZeroShotImageClassification.from_pretrained("ciderlab/siglip2-design-discriminator-backbone") - Notebooks
- Google Colab
- Kaggle
SigLIP2 Design Discriminator Backbone
Current backbone exported from the filtered Siamese replay checkpoint.
- Source checkpoint:
/scratch/gautschi/jasonwu/designsystem/design_discriminator_runs/repro-bal-p47-c15-min-20260621T042932Z/checkpoint/checkpoint.pt - Dataset source:
/scratch/gautschi/jasonwu/designsystem/amex_render_pairs_v2_local - Selection metric:
val_min_accuracy - Threshold:
0.5
See provenance.json for the full replay metadata.
- Downloads last month
- 58