Instructions to use masterhaniwa/CLIP_ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use masterhaniwa/CLIP_ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="masterhaniwa/CLIP_ft") 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, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("masterhaniwa/CLIP_ft") model = AutoModelForZeroShotImageClassification.from_pretrained("masterhaniwa/CLIP_ft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download best_model_9.pt from masterhaniwa/CLIP_ft: direct link, hf CLI and curl.
- Browser
- Download file 605 MB
-
https://huggingface.co/masterhaniwa/CLIP_ft/resolve/main/best_model_9.pt
- Command line
-
hf download hf://masterhaniwa/CLIP_ft/best_model_9.pt
-
curl -L -o best_model_9.pt https://huggingface.co/masterhaniwa/CLIP_ft/resolve/main/best_model_9.pt
605 MB
- Xet hash:
- 5fc971448871d339e5805adea5c4445e4877bd016be9404d5674e6b657656f40
- Size of remote file:
- 605 MB
- SHA256:
- dad9bcb012433572c010eb33063aa1ccb3766dbd1def1930bbc473c045b4b9b2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.