{
    "architectures": [
        "VideoMAEForVideoClassification"
    ],
    "attention_probs_dropout_prob": 0.0,
    "decoder_hidden_size": 384,
    "decoder_intermediate_size": 1536,
    "decoder_num_attention_heads": 6,
    "decoder_num_hidden_layers": 4,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "id2label": {
        "0": "drink water",
        "1": "brush teeth",
        "2": "pick up",
        "3": "reading",
        "4": "writing",
        "5": "cheer up",
        "6": "jump up",
        "7": "phone call",
        "8": "taking a selfie",
        "9": "salute"
    },
    "image_size": 224,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "label2id": {
        "drink water": 0,
        "brush teeth": 1,
        "pick up": 2,
        "reading": 3,
        "writing": 4,
        "cheer up": 5,
        "jump up": 6,
        "phone call": 7,
        "taking a selfie": 8,
        "salute": 9
    },
    "layer_norm_eps": 1e-12,
    "model_type": "videomae",
    "norm_pix_loss": false,
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_frames": 16,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "qkv_bias": true,
    "torch_dtype": "float32",
    "transformers_version": "4.21.0.dev0",
    "tubelet_size": 2,
    "use_mean_pooling": true
}