Instructions to use Lucas20250626/semanticgallery-mlx-siglip2-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lucas20250626/semanticgallery-mlx-siglip2-stage1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Lucas20250626/semanticgallery-mlx-siglip2-stage1") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Lucas20250626/semanticgallery-mlx-siglip2-stage1", dtype="auto") - MLX
How to use Lucas20250626/semanticgallery-mlx-siglip2-stage1 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir semanticgallery-mlx-siglip2-stage1 Lucas20250626/semanticgallery-mlx-siglip2-stage1
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
SemanticGallery MLX SigLIP2 Stage 1
This repository hosts the published Stage 1 weights used by SemanticGallery.
- Base model:
google/siglip2-base-patch16-224 - Runtime target:
MLXon Apple Silicon - Training path: public text-image alignment on Flickr30k and Screen2Words
SemanticGallery quick start downloads these Stage 1 weights automatically on first run. Stage 2 remains local and adapts the image encoder to the user's own gallery.
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for Lucas20250626/semanticgallery-mlx-siglip2-stage1
Base model
google/siglip2-base-patch16-224