{
  "_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large-one-to-many/",
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "add_bias_logits": false,
  "add_final_layer_norm": true,
  "architectures": [
    "MBartForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": true,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "gradient_checkpointing": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "max_length": 200,
  "max_position_embeddings": 1024,
  "model_type": "mbart",
  "normalize_before": true,
  "normalize_embedding": true,
  "num_beams": 5,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "scale_embedding": true,
  "static_position_embeddings": false,
  "transformers_version": "4.4.0.dev0",
  "use_cache": true,
  "vocab_size": 250054,
  "tokenizer_class": "MBart50Tokenizer"
}