config.json

{
  "_name_or_path": "microsoft/git-base-vqav2",
  "architectures": [
    "ViltForQuestionAnswering"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 101,
  "classifier_dropout": null,
  "eos_token_id": 102,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "gray",
    "1": "green",
    "2": "blue",
    "3": "sphere",
    "4": "red",
    "5": "brown",
    "6": "purple",
    "7": "cylinder",
    "8": "yellow",
    "9": "cube",
    "10": "cyan"
  },
  "image_size": 384,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "blue": 2,
    "brown": 5,
    "cube": 9,
    "cyan": 10,
    "cylinder": 7,
    "gray": 0,
    "green": 1,
    "purple": 6,
    "red": 4,
    "sphere": 3,
    "yellow": 8
  },
  "layer_norm_eps": 1e-12,
  "max_image_length": -1,
  "max_position_embeddings": 1024,
  "modality_type_vocab_size": 2,
  "model_type": "vilt",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 6,
  "num_image_with_embedding": null,
  "num_images": -1,
  "pad_token_id": 0,
  "patch_size": 32,
  "position_embedding_type": "absolute",
  "qkv_bias": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.35.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vision_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "quick_gelu",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 480,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "git_vision_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 16,
    "prefix": null,
    "problem_type": null,
    "projection_dim": 512,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.26.0.dev0",
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "vocab_size": 30522
}