config.json

{
  "architectures": [
    "Florence2ForConditionalGeneration"
  ],
  "image_token_id": 51289,
  "is_encoder_decoder": true,
  "model_type": "florence2",
  "text_config": {
    "activation_dropout": 0.1,
    "activation_function": "gelu",
    "add_bias_logits": false,
    "add_final_layer_norm": false,
    "attention_dropout": 0.1,
    "classif_dropout": 0.1,
    "classifier_dropout": 0.0,
    "d_model": 768,
    "decoder_attention_heads": 12,
    "decoder_ffn_dim": 3072,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 6,
    "dropout": 0.1,
    "early_stopping": true,
    "encoder_attention_heads": 12,
    "encoder_ffn_dim": 3072,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 6,
    "forced_bos_token_id": 0,
    "gradient_checkpointing": false,
    "init_std": 0.02,
    "max_position_embeddings": 1024,
    "model_type": "bart",
    "no_repeat_ngram_size": 3,
    "normalize_before": false,
    "num_beams": 3,
    "num_hidden_layers": 6,
    "scale_embedding": false,
    "use_cache": true,
    "vocab_size": 51328
  },
  "torch_dtype": "float16",
  "transformers_version": "4.56.0.dev0",
  "vision_config": {
    "activation_function": "gelu",
    "depths": [
      1,
      1,
      9,
      1
    ],
    "dim_embed": [
      128,
      256,
      512,
      1024
    ],
    "drop_path_rate": 0.1,
    "embed_dim": [
      128,
      256,
      512,
      1024
    ],
    "enable_checkpoint": false,
    "image_feature_source": [
      "spatial_avg_pool",
      "temporal_avg_pool"
    ],
    "image_pos_embed": {
      "max_pos_embeddings": 50,
      "type": "learned_abs_2d"
    },
    "in_channels": 3,
    "initializer_range": 0.02,
    "max_pos_embeddings": 50,
    "max_position_embeddings": 50,
    "max_temporal_embeddings": 100,
    "mlp_ratio": 4.0,
    "model_type": "florence_vision",
    "num_groups": [
      4,
      8,
      16,
      32
    ],
    "num_heads": [
      4,
      8,
      16,
      32
    ],
    "patch_padding": [
      3,
      1,
      1,
      1
    ],
    "patch_prenorm": [
      false,
      true,
      true,
      true
    ],
    "patch_size": [
      7,
      3,
      3,
      3
    ],
    "patch_stride": [
      4,
      2,
      2,
      2
    ],
    "projection_dim": 768,
    "qkv_bias": true,
    "visual_temporal_embedding": {
      "max_temporal_embeddings": 100,
      "type": "COSINE"
    },
    "window_size": 12
  }
}