How to use pySilver/marqo-fashionSigLIP-ST with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:pySilver/marqo-fashionSigLIP-ST') tokenizer = open_clip.get_tokenizer('hf-hub:pySilver/marqo-fashionSigLIP-ST')
How to use pySilver/marqo-fashionSigLIP-ST with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="pySilver/marqo-fashionSigLIP-ST", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, SigLIP processor = AutoProcessor.from_pretrained("pySilver/marqo-fashionSigLIP-ST", trust_remote_code=True) model = SigLIP.from_pretrained("pySilver/marqo-fashionSigLIP-ST", trust_remote_code=True, device_map="auto")
How to use pySilver/marqo-fashionSigLIP-ST with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('zero-shot-image-classification', 'pySilver/marqo-fashionSigLIP-ST');
https://huggingface.co/pySilver/marqo-fashionSigLIP-ST/resolve/main/tokenizer.json
hf download hf://pySilver/marqo-fashionSigLIP-ST/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/pySilver/marqo-fashionSigLIP-ST/resolve/main/tokenizer.json
