config.json

{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "gpt2_base",
    "activation_function": "gelu_new",
    "add_cross_attention": true,
    "architectures": [
      "GPT2LMHeadModel"
    ],
    "attn_pdrop": 0.1,
    "embd_pdrop": 0.1,
    "initializer_range": 0.02,
    "is_decoder": true,
    "layer_norm_epsilon": 1e-05,
    "model_type": "gpt2",
    "n_embd": 768,
    "n_head": 12,
    "n_inner": null,
    "n_layer": 6,
    "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,
    "torch_dtype": "bfloat16",
    "type_vocab_size": 1,
    "use_cache": true,
    "vocab_size": 30002
  },
  "decoder_start_token_id": 0,
  "encoder": {
    "_name_or_path": "encoder",
    "architectures": [
      "SwinModel"
    ],
    "attention_probs_dropout_prob": 0.0,
    "depths": [
      2,
      2,
      18,
      2
    ],
    "drop_path_rate": 0.1,
    "embed_dim": 96,
    "encoder_stride": 32,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "image_size": 224,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-05,
    "mlp_ratio": 4.0,
    "model_type": "swin",
    "num_channels": 3,
    "num_heads": [
      3,
      6,
      12,
      24
    ],
    "num_layers": 4,
    "out_features": [
      "stage4"
    ],
    "out_indices": [
      4
    ],
    "patch_size": 4,
    "path_norm": true,
    "qkv_bias": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "torch_dtype": "bfloat16",
    "use_absolute_embeddings": false,
    "window_size": 7
  },
  "eos_token_id": 30000,
  "is_encoder_decoder": true,
  "max_length": null,
  "model_type": "vision-encoder-decoder",
  "pad_token_id": 1,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.4",
  "vocab_size": 30002
}