Instructions to use juns/CS-CLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use juns/CS-CLIP with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:juns/CS-CLIP') tokenizer = open_clip.get_tokenizer('hf-hub:juns/CS-CLIP') - Notebooks
- Google Colab
- Kaggle
Download config.json from juns/CS-CLIP: direct link, hf CLI and curl.
- Browser
- Download file 484 Bytes
-
https://huggingface.co/juns/CS-CLIP/resolve/main/config.json
- Command line
-
hf download hf://juns/CS-CLIP/config.json
-
curl -L -o config.json https://huggingface.co/juns/CS-CLIP/resolve/main/config.json
484 Bytes
| { | |
| "_name_or_path": "openai/clip-vit-base-patch32", | |
| "architectures": [ | |
| "CLIPModel" | |
| ], | |
| "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": "4.44.2", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "model_type": "clip_vision_model" | |
| } | |
| } | |