config.json

{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "bos_token_id": 50256,
  "decoder": {
    "activation_function": "gelu_new",
    "add_cross_attention": true,
    "architectures": [
      "GPT2LMHeadModel"
    ],
    "attn_pdrop": 0.1,
    "decoder_start_token_id": 50256,
    "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,
    "pad_token_id": 50256,
    "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
      }
    },
    "torch_dtype": "float32",
    "use_cache": true,
    "vocab_size": 50257
  },
  "decoder_start_token_id": 50256,
  "encoder": {
    "architectures": [
      "ViTModel"
    ],
    "attention_probs_dropout_prob": 0.0,
    "encoder_stride": 16,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "image_size": 224,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-12,
    "model_type": "vit",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "pooler_act": "tanh",
    "pooler_output_size": 768,
    "qkv_bias": true,
    "torch_dtype": "float32"
  },
  "eos_token_id": 50256,
  "is_encoder_decoder": true,
  "model_type": "vision-encoder-decoder",
  "pad_token_id": 50256,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "use_cache": true
}