Instructions to use fpsandnoob/mae-vit-base-patch32-224-ct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fpsandnoob/mae-vit-base-patch32-224-ct with Transformers:
# Load model directly from transformers import AutoImageProcessor, AutoModelForPreTraining processor = AutoImageProcessor.from_pretrained("fpsandnoob/mae-vit-base-patch32-224-ct") model = AutoModelForPreTraining.from_pretrained("fpsandnoob/mae-vit-base-patch32-224-ct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from fpsandnoob/mae-vit-base-patch32-224-ct: direct link, hf CLI and curl.
- Browser
- Download file 731 Bytes
-
https://huggingface.co/fpsandnoob/mae-vit-base-patch32-224-ct/resolve/main/config.json
- Command line
-
hf download hf://fpsandnoob/mae-vit-base-patch32-224-ct/config.json
-
curl -L -o config.json https://huggingface.co/fpsandnoob/mae-vit-base-patch32-224-ct/resolve/main/config.json
731 Bytes
| { | |
| "_name_or_path": "google/vit-base-patch32-224-in21k", | |
| "architectures": [ | |
| "ViTMAEForPreTraining" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "decoder_hidden_size": 512, | |
| "decoder_intermediate_size": 2048, | |
| "decoder_num_attention_heads": 16, | |
| "decoder_num_hidden_layers": 8, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "mask_ratio": 0.75, | |
| "model_type": "vit_mae", | |
| "norm_pix_loss": true, | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 32, | |
| "qkv_bias": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.27.0.dev0" | |
| } | |