config.json

{
  "architectures": [
    "EncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
    "add_cross_attention": true,
    "architectures": [
      "BertForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "classifier_dropout": null,
    "dtype": "float32",
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": true,
    "layer_norm_eps": 1e-12,
    "max_position_embeddings": 512,
    "model_type": "bert",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "output_past": true,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "type_vocab_size": 2,
    "use_cache": true,
    "vocab_size": 31002
  },
  "decoder_start_token_id": 4,
  "dtype": "float32",
  "encoder": {
    "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
    "architectures": [
      "BertForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "classifier_dropout": null,
    "dtype": "float32",
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-12,
    "max_position_embeddings": 512,
    "model_type": "bert",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "output_past": true,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "type_vocab_size": 2,
    "use_cache": true,
    "vocab_size": 31002
  },
  "eos_token_id": 5,
  "is_encoder_decoder": true,
  "model_type": "encoder-decoder",
  "pad_token_id": 1,
  "transformers_version": "4.56.2",
  "vocab_size": 31002
}