aroot/first_run_lines
035
1{2 "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",3 "_num_labels": 3,4 "activation_dropout": 0.0,5 "activation_function": "relu",6 "add_bias_logits": false,7 "add_final_layer_norm": true,8 "architectures": [9 "MBartForConditionalGeneration"10 ],11 "attention_dropout": 0.0,12 "bos_token_id": 0,13 "classif_dropout": 0.0,14 "classifier_dropout": 0.0,15 "d_model": 1024,16 "decoder_attention_heads": 16,17 "decoder_ffn_dim": 4096,18 "decoder_layerdrop": 0.0,19 "decoder_layers": 12,20 "decoder_start_token_id": 2,21 "dropout": 0.1,22 "early_stopping": true,23 "encoder_attention_heads": 16,24 "encoder_ffn_dim": 4096,25 "encoder_layerdrop": 0.0,26 "encoder_layers": 12,27 "eos_token_id": 2,28 "forced_eos_token_id": 2,29 "gradient_checkpointing": false,30 "id2label": {31 "0": "LABEL_0",32 "1": "LABEL_1",33 "2": "LABEL_2"34 },35 "init_std": 0.02,36 "is_encoder_decoder": true,37 "label2id": {38 "LABEL_0": 0,39 "LABEL_1": 1,40 "LABEL_2": 241 },42 "max_length": 200,43 "max_position_embeddings": 1024,44 "model_type": "mbart",45 "normalize_before": true,46 "normalize_embedding": true,47 "num_beams": 5,48 "num_hidden_layers": 12,49 "output_past": true,50 "pad_token_id": 1,51 "scale_embedding": true,52 "static_position_embeddings": false,53 "tokenizer_class": "MBart50Tokenizer",54 "torch_dtype": "float32",55 "transformers_version": "4.30.2",56 "use_cache": true,57 "vocab_size": 25005458}59 