Instructions to use laion/CLIP-ViT-bigG-14-laion2B-39B-b160k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use laion/CLIP-ViT-bigG-14-laion2B-39B-b160k with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:laion/CLIP-ViT-bigG-14-laion2B-39B-b160k') tokenizer = open_clip.get_tokenizer('hf-hub:laion/CLIP-ViT-bigG-14-laion2B-39B-b160k') - Notebooks
- Google Colab
- Kaggle
How to solve running errors
1
#19 opened almost 2 years ago
by
substX
Image - Text Similarity
#17 opened about 2 years ago
by
StarGazer-Media
ETÀ on Getting Started section completion
#16 opened over 2 years ago
by
tuhinmallick02
Model card has 0 info how to use amazing! I want to use ViT-bigG-14, laion2b_s39b_b160k to generate captions for a given folder of images
3
#13 opened over 2 years ago
by
MonsterMMORPG
Make a pruned version version
3
#9 opened almost 3 years ago
by
Kwissbeats
Correrct Transformers Pad Token
3
#7 opened about 3 years ago
by
patrickvonplaten
How to use laion/CLIP-ViT-bigG-14-laion2B-39B-b160k to calculate similarity score of given 2 images?
4
#5 opened over 3 years ago
by
MonsterMMORPG