| { |
| "architectures": [ |
| "ViTForImageClassification" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "dtype": "float32", |
| "encoder_stride": 16, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "cruiser", |
| "1": "naked", |
| "2": "roller", |
| "3": "sport" |
| }, |
| "image_size": 224, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "cruiser": 0, |
| "naked": 1, |
| "roller": 2, |
| "sport": 3 |
| }, |
| "layer_norm_eps": 1e-12, |
| "model_type": "vit", |
| "num_attention_heads": 12, |
| "num_channels": 3, |
| "num_hidden_layers": 12, |
| "patch_size": 16, |
| "pooler_act": "tanh", |
| "pooler_output_size": 768, |
| "problem_type": "single_label_classification", |
| "qkv_bias": true, |
| "transformers_version": "5.5.0", |
| "use_cache": false |
| } |
|
|
