config.json

{
  "_name_or_path": "MCG-NJU/videomae-huge-finetuned-kinetics",
  "architectures": [
    "VideoMAEForVideoClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "decoder_hidden_size": 640,
  "decoder_intermediate_size": 2560,
  "decoder_num_attention_heads": 8,
  "decoder_num_hidden_layers": 12,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 1280,
  "id2label": {
    "0": "00",
    "1": "01",
    "2": "02",
    "3": "03",
    "4": "04",
    "5": "05",
    "6": "06",
    "7": "07",
    "8": "08",
    "9": "09",
    "10": "10",
    "11": "11",
    "12": "12",
    "13": "13",
    "14": "14",
    "15": "15",
    "16": "16"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "label2id": {
    "00": 0,
    "01": 1,
    "02": 2,
    "03": 3,
    "04": 4,
    "05": 5,
    "06": 6,
    "07": 7,
    "08": 8,
    "09": 9,
    "10": 10,
    "11": 11,
    "12": 12,
    "13": 13,
    "14": 14,
    "15": 15,
    "16": 16
  },
  "layer_norm_eps": 1e-12,
  "model_type": "videomae",
  "norm_pix_loss": true,
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_frames": 16,
  "num_hidden_layers": 32,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "tubelet_size": 2,
  "use_mean_pooling": true
}