{ "_num_labels": 3, "activation_dropout": 0.0, "activation_function": "swish", "add_bias_logits": false, "add_final_layer_norm": false, "architectures": [ "MarianMTModel" ], "attention_dropout": 0.0, "bad_words_ids": [ [ 58100 ] ], "bos_token_id": 0, "classif_dropout": 0.0, "d_model": 2, "decoder_attention_heads": 1, "decoder_ffn_dim": 2, "decoder_layerdrop": 0.0, "decoder_layers": 2, "decoder_start_token_id": 58100, "dropout": 0.1, "encoder_attention_heads": 1, "encoder_ffn_dim": 2, "encoder_layerdrop": 0.0, "encoder_layers": 2, "eos_token_id": 0, "extra_pos_embeddings": 58101, "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_position_embeddings": 512, "model_type": "marian", "normalize_before": false, "normalize_embedding": false, "num_beams": 2, "num_hidden_layers": 6, "pad_token_id": 58100, "scale_embedding": true, "static_position_embeddings": true, "vocab_size": 58101 }