{
  "additional_vocab_size": 0,
  "alpha_initializer": "zeros",
  "alpha_type": "float",
  "alphas_initializer_range": 0.0,
  "architectures": [
    "IdeficsForVisionText2Text"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 1,
  "cross_layer_interval": 1,
  "dropout": 0.0,
  "eos_token_id": 2,
  "freeze_lm_head": false,
  "freeze_text_layers": true,
  "freeze_text_module_exceptions": [],
  "freeze_vision_layers": true,
  "freeze_vision_module_exceptions": [],
  "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
  },
  "max_position_embeddings": 512,
  "modality_type_vocab_size": 2,
  "model_type": "idefics",
  "num_attention_heads": 4,
  "num_channels": 3,
  "num_hidden_layers": 5,
  "num_images": -1,
  "pad_token_id": 0,
  "patch_size": 2,
  "perceiver_config": {
    "model_type": "idefics"
  },
  "qk_layer_norms": false,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.33.0.dev0",
  "type_vocab_size": 16,
  "use_cache": true,
  "use_resampler": false,
  "vision_config": {
    "embed_dim": 32,
    "image_size": 30,
    "intermediate_size": 37,
    "model_type": "idefics",
    "num_attention_heads": 4,
    "num_hidden_layers": 5,
    "patch_size": 2
  },
  "vocab_size": 32002
}