{
  "_name_or_path": "google/vit-hybrid-base-bit-384",
  "architectures": [
    "ViTHybridForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "backbone": null,
  "backbone_config": {
    "depths": [
      3,
      4,
      9
    ],
    "embedding_dynamic_padding": true,
    "global_padding": "SAME",
    "layer_type": "bottleneck",
    "model_type": "bit",
    "out_features": [
      "stage3"
    ],
    "out_indices": [
      3
    ],
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3"
    ]
  },
  "backbone_featmap_shape": [
    1,
    1024,
    24,
    24
  ],
  "backbone_kwargs": null,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "negative",
    "1": "positive"
  },
  "image_size": 384,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "negative": 0,
    "positive": 1
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit-hybrid",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 1,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "use_pretrained_backbone": false,
  "use_timm_backbone": false
}