Instructions to use macqueen01/sonigo-CLIP-tagger with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use macqueen01/sonigo-CLIP-tagger with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("macqueen01/sonigo-CLIP-tagger") model = AutoModel.from_pretrained("macqueen01/sonigo-CLIP-tagger", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from macqueen01/sonigo-CLIP-tagger: direct link, hf CLI and curl.
- Browser
- Download file 491 Bytes
-
https://huggingface.co/macqueen01/sonigo-CLIP-tagger/resolve/main/config.json
- Command line
-
hf download hf://macqueen01/sonigo-CLIP-tagger/config.json
-
curl -L -o config.json https://huggingface.co/macqueen01/sonigo-CLIP-tagger/resolve/main/config.json
491 Bytes
| { | |
| "_name_or_path": "openai/clip-vit-base-patch32", | |
| "architectures": [ | |
| "SoftmaxCLIPModel" | |
| ], | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "projection_dim": 512, | |
| "text_config": { | |
| "bos_token_id": 0, | |
| "dropout": 0.0, | |
| "eos_token_id": 2, | |
| "model_type": "clip_text_model" | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "model_type": "clip_vision_model" | |
| } | |
| } | |