rdj-034/lab2_efficient

1{2  "_num_labels": 3,3  "activation_dropout": 0.0,4  "activation_function": "swish",5  "add_bias_logits": false,6  "add_final_layer_norm": false,7  "architectures": [8    "MarianMTModel"9  ],10  "attention_dropout": 0.0,11  "bos_token_id": 0,12  "classif_dropout": 0.0,13  "classifier_dropout": 0.0,14  "d_model": 512,15  "decoder_attention_heads": 8,16  "decoder_ffn_dim": 2048,17  "decoder_layerdrop": 0.0,18  "decoder_layers": 6,19  "decoder_start_token_id": 59513,20  "decoder_vocab_size": 59514,21  "dropout": 0.1,22  "dtype": "float32",23  "encoder_attention_heads": 8,24  "encoder_ffn_dim": 2048,25  "encoder_layerdrop": 0.0,26  "encoder_layers": 6,27  "eos_token_id": 0,28  "gradient_checkpointing": false,29  "id2label": {30    "0": "LABEL_0",31    "1": "LABEL_1",32    "2": "LABEL_2"33  },34  "init_std": 0.02,35  "is_decoder": false,36  "is_encoder_decoder": true,37  "label2id": {38    "LABEL_0": 0,39    "LABEL_1": 1,40    "LABEL_2": 241  },42  "max_position_embeddings": 512,43  "model_type": "marian",44  "normalize_before": false,45  "normalize_embedding": false,46  "num_hidden_layers": 6,47  "pad_token_id": 59513,48  "scale_embedding": true,49  "share_encoder_decoder_embeddings": true,50  "static_position_embeddings": true,51  "tie_word_embeddings": true,52  "transformers_version": "5.0.0",53  "use_cache": false,54  "vocab_size": 5951455}56