config.json

{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "gpt2",
    "activation_function": "gelu_new",
    "add_cross_attention": true,
    "architectures": [
      "GPT2LMHeadModel"
    ],
    "attn_pdrop": 0.1,
    "dtype": "float32",
    "embd_pdrop": 0.1,
    "initializer_range": 0.02,
    "is_decoder": true,
    "layer_norm_epsilon": 1e-05,
    "model_type": "gpt2",
    "n_ctx": 1024,
    "n_embd": 768,
    "n_head": 12,
    "n_inner": null,
    "n_layer": 12,
    "n_positions": 1024,
    "reorder_and_upcast_attn": false,
    "resid_pdrop": 0.1,
    "scale_attn_by_inverse_layer_idx": false,
    "scale_attn_weights": true,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "task_specific_params": {
      "text-generation": {
        "do_sample": true,
        "max_length": 50
      }
    },
    "use_cache": true,
    "vocab_size": 50304
  },
  "decoder_start_token_id": 50287,
  "dtype": "float32",
  "encoder": {
    "_name_or_path": "microsoft/dit-base",
    "add_fpn": false,
    "architectures": [
      "BeitForMaskedImageModeling"
    ],
    "attention_probs_dropout_prob": 0.0,
    "auxiliary_channels": 256,
    "auxiliary_concat_input": false,
    "auxiliary_loss_weight": 0.4,
    "auxiliary_num_convs": 1,
    "drop_path_rate": 0.1,
    "dtype": "float32",
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "image_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "interpolate_pos_encoding": true,
    "layer_norm_eps": 1e-12,
    "layer_scale_init_value": 0.1,
    "model_type": "beit",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "out_features": [
      "stage3",
      "stage5",
      "stage7",
      "stage11"
    ],
    "out_indices": [
      3,
      5,
      7,
      11
    ],
    "patch_size": 16,
    "pool_scales": [
      1,
      2,
      3,
      6
    ],
    "reshape_hidden_states": true,
    "semantic_loss_ignore_index": 255,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12"
    ],
    "use_absolute_position_embeddings": true,
    "use_auxiliary_head": true,
    "use_mask_token": true,
    "use_mean_pooling": true,
    "use_relative_position_bias": false,
    "use_shared_relative_position_bias": false,
    "vocab_size": 8192
  },
  "eos_token_id": 50256,
  "is_encoder_decoder": true,
  "max_length": null,
  "model_type": "vision-encoder-decoder",
  "no_repeat_ngram_size": null,
  "pad_token_id": 50257,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.6"
}