config.json

{
  "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
  "_num_labels": 3,
  "activation_dropout": 0.1,
  "activation_function": "relu",
  "adaptor_activation_function": "gelu",
  "adaptor_dropout": 0.1,
  "adaptor_hidden_size": 512,
  "adaptor_init_std": 0.02,
  "adaptor_scaling_factor": 1.0,
  "adaptor_tuning": false,
  "add_bias_logits": false,
  "add_final_layer_norm": true,
  "additional_source_wait_k": -1,
  "alibi_encoding": false,
  "architectures": [
    "MBartForConditionalGeneration"
  ],
  "asymmetric_alibi_encoding": false,
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "bottleneck_mid_fusion_tokens": 4,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_adaptor_tying_config": null,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 2,
  "decoder_tying_config": null,
  "deep_adaptor_tuning": false,
  "deep_adaptor_tuning_ffn_only": false,
  "dropout": 0.1,
  "early_stopping": true,
  "embed_low_rank_dim": 0,
  "encoder_adaptor_tying_config": null,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "encoder_tying_config": null,
  "eos_token_id": 2,
  "expert_ffn_size": 128,
  "features_embed_dims": null,
  "features_vocab_sizes": null,
  "forced_eos_token_id": 2,
  "gradient_checkpointing": false,
  "gradient_reversal_for_domain_classifier": false,
  "hypercomplex": false,
  "hypercomplex_n": 2,
  "ia3_adaptors": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "initialization_scheme": "static",
  "inititialization_scheme": "static",
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "layernorm_adaptor_input": false,
  "layernorm_prompt_projection": false,
  "lora_adaptor_rank": 2,
  "lora_adaptors": false,
  "max_length": 200,
  "max_position_embeddings": 1024,
  "mid_fusion_layers": 3,
  "model_type": "mbart",
  "moe_adaptors": false,
  "multi_source": false,
  "multi_source_method": null,
  "multilayer_softmaxing": null,
  "no_embed_norm": false,
  "no_positional_encoding_decoder": false,
  "no_positional_encoding_encoder": false,
  "no_projection_prompt": false,
  "no_scale_attention_embedding": false,
  "normalize_before": true,
  "normalize_embedding": true,
  "num_beams": 5,
  "num_domains_for_domain_classifier": -1,
  "num_experts": 8,
  "num_hidden_layers": 12,
  "num_moe_adaptor_experts": 4,
  "num_prompts": 100,
  "num_sparsify_blocks": 8,
  "output_past": true,
  "pad_token_id": 1,
  "parallel_adaptors": false,
  "positional_encodings": false,
  "postnorm_decoder": false,
  "postnorm_encoder": false,
  "prompt_dropout": 0.1,
  "prompt_init_std": 0.02,
  "prompt_projection_hidden_size": 4096,
  "prompt_tuning": false,
  "recurrent_projections": 1,
  "residual_connection_adaptor": false,
  "residual_connection_prompt": false,
  "rope_encoding": false,
  "scale_embedding": true,
  "softmax_bias_tuning": false,
  "softmax_temperature": 1.0,
  "sparsification_temperature": 3.0,
  "sparsify_attention": false,
  "sparsify_ffn": false,
  "static_position_embeddings": false,
  "target_vocab_size": 0,
  "temperature_calibration": false,
  "tokenizer_class": "MBart50Tokenizer",
  "transformers_version": "4.3.2",
  "unidirectional_encoder": false,
  "use_cache": true,
  "use_moe": false,
  "use_tanh_activation_prompt": false,
  "vocab_size": 250054,
  "wait_k": -1
}