Instructions to use cs-giung/clip-vit-gigantic-patch14-fullcc2.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-giung/clip-vit-gigantic-patch14-fullcc2.5b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="cs-giung/clip-vit-gigantic-patch14-fullcc2.5b") 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("cs-giung/clip-vit-gigantic-patch14-fullcc2.5b") model = AutoModelForZeroShotImageClassification.from_pretrained("cs-giung/clip-vit-gigantic-patch14-fullcc2.5b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from cs-giung/clip-vit-gigantic-patch14-fullcc2.5b: direct link, hf CLI and curl.
- Browser
- Download file 666 Bytes
-
https://huggingface.co/cs-giung/clip-vit-gigantic-patch14-fullcc2.5b/resolve/main/config.json
- Command line
-
hf download hf://cs-giung/clip-vit-gigantic-patch14-fullcc2.5b/config.json
-
curl -L -o config.json https://huggingface.co/cs-giung/clip-vit-gigantic-patch14-fullcc2.5b/resolve/main/config.json
666 Bytes
| { | |
| "architectures": [ | |
| "CLIPModel" | |
| ], | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "projection_dim": 1280, | |
| "text_config": { | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 1280, | |
| "intermediate_size": 5120, | |
| "model_type": "clip_text_model", | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 32 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.0", | |
| "vision_config": { | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 1664, | |
| "intermediate_size": 8192, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 48, | |
| "patch_size": 14 | |
| } | |
| } | |