Feature Extraction
Transformers
Safetensors
English
clip
zero-shot-image-classification
CLIP
SigLIP
contrastive-learning
dual-encoder
vision-language
image-text-retrieval
huggingface
Instructions to use Amirhossein75/Image-Contrastive-CLIP-Flickr30k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Amirhossein75/Image-Contrastive-CLIP-Flickr30k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Amirhossein75/Image-Contrastive-CLIP-Flickr30k")# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("Amirhossein75/Image-Contrastive-CLIP-Flickr30k") model = AutoModelForZeroShotImageClassification.from_pretrained("Amirhossein75/Image-Contrastive-CLIP-Flickr30k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- de73757ed076eeb7cbabf8c3e074c3fb428def5765451177c0de1976c729f3ff
- Size of remote file:
- 599 MB
- SHA256:
- c25dc7ea3a2965c381252d2370b27c150e8889daee5e85e30a65e9253307df84
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.