{
  "architectures": [
    "TimesformerForVideoClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "attention_type": "divided_space_time",
  "drop_path_rate": 0,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4
  },
  "layer_norm_eps": 1e-06,
  "model_type": "timesformer",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_frames": 8,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.53.3"
}