config.json

{
  "architectures": [
    "ViltForQuestionAnswering"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 32,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "image_size": 30,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "layer_norm_eps": 1e-12,
  "max_image_length": -1,
  "max_position_embeddings": 512,
  "modality_type_vocab_size": 2,
  "model_type": "vilt",
  "num_attention_heads": 4,
  "num_channels": 3,
  "num_hidden_layers": 5,
  "num_images": -1,
  "patch_size": 2,
  "qkv_bias": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.28.0.dev0",
  "type_vocab_size": 16,
  "vocab_size": 1124
}