Instructions to use hf-tiny-model-private/tiny-random-ViTForImageClassification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-tiny-model-private/tiny-random-ViTForImageClassification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="hf-tiny-model-private/tiny-random-ViTForImageClassification") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("hf-tiny-model-private/tiny-random-ViTForImageClassification") model = AutoModelForImageClassification.from_pretrained("hf-tiny-model-private/tiny-random-ViTForImageClassification") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "tiny_models/vit/ViTForImageClassification", | |
| "architectures": [ | |
| "ViTForImageClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "encoder_stride": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "image_size": 30, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "layer_norm_eps": 1e-12, | |
| "model_type": "vit", | |
| "num_attention_heads": 4, | |
| "num_channels": 3, | |
| "num_hidden_layers": 5, | |
| "patch_size": 2, | |
| "qkv_bias": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.28.0.dev0" | |
| } | |