Zero-Shot Image Classification
Transformers
Safetensors
siglip
vision
medical
radiology
dermatology
pathology
ophthalmology
chest-x-ray
Instructions to use fokan/MedSigLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fokan/MedSigLIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="fokan/MedSigLIP") 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("fokan/MedSigLIP") model = AutoModelForZeroShotImageClassification.from_pretrained("fokan/MedSigLIP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from fokan/MedSigLIP: direct link, hf CLI and curl.
- Browser
- Download file 455 Bytes
-
https://huggingface.co/fokan/MedSigLIP/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://fokan/MedSigLIP/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/fokan/MedSigLIP/resolve/main/special_tokens_map.json
455 Bytes
| { | |
| "eos_token": { | |
| "content": "</s>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "</s>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<unk>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false | |
| } | |
| } | |