{
  "_name_or_path": "microsoft/Florence-2-base",
  "architectures": [
    "Florence2ForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "microsoft/Florence-2-base--configuration_florence2.Florence2Config",
    "AutoModelForCausalLM": "microsoft/Florence-2-base--modeling_florence2.Florence2ForConditionalGeneration"
  },
  "bos_token_id": 0,
  "eos_token_id": 2,
  "ignore_index": -100,
  "is_encoder_decoder": true,
  "model_type": "florence2",
  "pad_token_id": 1,
  "projection_dim": 768,
  "text_config": {
    "_name_or_path": "",
    "activation_dropout": 0.1,
    "activation_function": "gelu",
    "add_bias_logits": false,
    "add_cross_attention": false,
    "add_final_layer_norm": false,
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classif_dropout": 0.1,
    "classifier_dropout": 0.0,
    "cross_attention_hidden_size": null,
    "d_model": 768,
    "decoder_attention_heads": 12,
    "decoder_ffn_dim": 3072,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 6,
    "decoder_start_token_id": 2,
    "dropout": 0.1,
    "encoder_attention_heads": 12,
    "encoder_ffn_dim": 3072,
    "encoder_layers": 6,
    "is_decoder": false,
    "is_encoder_decoder": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1,
      "LABEL_2": 2
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 1024,
    "model_type": "florence2_language",
    "no_repeat_ngram_size": 3,
    "num_beam_groups": 1,
    "num_beams": 3,
    "num_hidden_layers": 6,
    "pad_token_id": 1,
    "return_dict": true
  },
  "torch_dtype": "float32",
  "transformers_version": "4.45.2",
  "vision_config": {
    "add_cross_attention": false,
    "architectures": null,
    "depths": [1, 1, 9, 1],
    "dim_embed": [128, 256, 512, 1024],
    "drop_path_rate": 0.1,
    "image_feature_source": ["spatial_avg_pool", "temporal_avg_pool"],
    "image_pos_embed": {
      "max_pos_embeddings": 50,
      "type": "learned_abs_2d"
    },
    "model_type": "davit",  // This is the required change
    "num_groups": [4, 8, 16, 32],
    "num_heads": [4, 8, 16, 32],
    "patch_padding": [3, 1, 1, 1],
    "patch_size": [7, 3, 3, 3],
    "patch_stride": [4, 2, 2, 2],
    "projection_dim": 768,
    "visual_temporal_embedding": {
      "max_temporal_embeddings": 100,
      "type": "COSINE"
    },
    "window_size": 12
  },
  "vocab_size": 51289
}