config.json

{
  "architectures": [
    "Florence2Model"
  ],
  "dtype": "float32",
  "image_token_id": 4,
  "initializer_range": 0.02,
  "is_encoder_decoder": true,
  "model_type": "florence2",
  "text_config": {
    "activation_dropout": 0.1,
    "activation_function": "gelu",
    "attention_dropout": 0.1,
    "bos_token_id": 0,
    "classifier_dropout": 0.0,
    "d_model": 16,
    "decoder_attention_heads": 1,
    "decoder_ffn_dim": 16,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 1,
    "decoder_start_token_id": 2,
    "dropout": 0.1,
    "encoder_attention_heads": 1,
    "encoder_ffn_dim": 16,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 1,
    "eos_token_id": 2,
    "forced_eos_token_id": 2,
    "init_std": 0.02,
    "is_decoder": false,
    "max_position_embeddings": 200,
    "model_type": "bart",
    "pad_token_id": 1,
    "scale_embedding": false,
    "tie_word_embeddings": true,
    "use_cache": true,
    "vocab_size": 51290
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.16.0.dev0",
  "vision_config": {
    "activation_function": "gelu",
    "depths": [
      1
    ],
    "drop_path_rate": 0.1,
    "embed_dim": [
      16
    ],
    "in_channels": 3,
    "initializer_range": 0.02,
    "max_position_embeddings": 50,
    "max_temporal_embeddings": 100,
    "mlp_ratio": 4.0,
    "model_type": "florence_vision",
    "num_groups": [
      1
    ],
    "num_heads": [
      1
    ],
    "patch_padding": [
      3
    ],
    "patch_prenorm": [
      false
    ],
    "patch_size": [
      7
    ],
    "patch_stride": [
      4
    ],
    "projection_dim": 16,
    "qkv_bias": true,
    "window_size": 12
  }
}