Instructions to use timm/ViT-SO400M-14-SigLIP-384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use timm/ViT-SO400M-14-SigLIP-384 with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:timm/ViT-SO400M-14-SigLIP-384') tokenizer = open_clip.get_tokenizer('hf-hub:timm/ViT-SO400M-14-SigLIP-384') - Notebooks
- Google Colab
- Kaggle
Memory Requirements
#7 opened over 1 year ago
by
Shreays
How do get the embeddings from the inference api?
#6 opened almost 2 years ago
by
jthomm2
Cannot reproduce inference API result
3
#5 opened about 2 years ago
by
aliencaocao
Very flat output? "Probabilities" all close to zero.
13
#3 opened over 2 years ago
by
Moghrua