config.json

{
  "_name_or_path": "dandelin/vilt-b32-mlm",
  "architectures": [
    "ViltForQuestionAnswering"
  ],
  "attention_probs_dropout_prob": 0.0,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "skateboard",
    "1": "down",
    "2": "no",
    "3": "chopsticks",
    "4": "at table",
    "5": "table",
    "6": "picnic table",
    "7": "crossing",
    "8": "walking",
    "9": "shrimp",
    "10": "ice cream",
    "11": "4",
    "12": "yes",
    "13": "watching",
    "14": "1"
  },
  "image_size": 384,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "1": 14,
    "4": 11,
    "at table": 4,
    "chopsticks": 3,
    "crossing": 7,
    "down": 1,
    "ice cream": 10,
    "no": 2,
    "picnic table": 6,
    "shrimp": 9,
    "skateboard": 0,
    "table": 5,
    "walking": 8,
    "watching": 13,
    "yes": 12
  },
  "layer_norm_eps": 1e-12,
  "max_image_length": -1,
  "max_position_embeddings": 40,
  "modality_type_vocab_size": 2,
  "model_type": "vilt",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "num_images": -1,
  "patch_size": 32,
  "qkv_bias": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.40.1",
  "type_vocab_size": 2,
  "vocab_size": 30522
}