Israhassan/EncoderDecoder

1{2  "_name_or_path": "facebook/bart-large",3  "activation_dropout": 0.1,4  "activation_function": "gelu",5  "add_bias_logits": false,6  "add_final_layer_norm": false,7  "architectures": [8    "BartForSequenceClassification"9  ],10  "attention_dropout": 0.1,11  "bos_token_id": 0,12  "classif_dropout": 0.1,13  "classifier_dropout": 0.0,14  "d_model": 1024,15  "decoder_attention_heads": 16,16  "decoder_ffn_dim": 4096,17  "decoder_layerdrop": 0.0,18  "decoder_layers": 12,19  "decoder_start_token_id": 2,20  "dropout": 0.1,21  "early_stopping": true,22  "encoder_attention_heads": 16,23  "encoder_ffn_dim": 4096,24  "encoder_layerdrop": 0.0,25  "encoder_layers": 12,26  "eos_token_id": 2,27  "forced_bos_token_id": 0,28  "forced_eos_token_id": 2,29  "gradient_checkpointing": false,30  "id2label": {31    "0": "LABEL_0",32    "1": "LABEL_1"33  },34  "init_std": 0.02,35  "is_encoder_decoder": true,36  "label2id": {37    "LABEL_0": 0,38    "LABEL_1": 139  },40  "max_position_embeddings": 1024,41  "model_type": "bart",42  "no_repeat_ngram_size": 3,43  "normalize_before": false,44  "num_beams": 4,45  "num_hidden_layers": 12,46  "pad_token_id": 1,47  "scale_embedding": false,48  "task_specific_params": {49    "summarization": {50      "length_penalty": 1.0,51      "max_length": 128,52      "min_length": 12,53      "num_beams": 454    },55    "summarization_cnn": {56      "length_penalty": 2.0,57      "max_length": 142,58      "min_length": 56,59      "num_beams": 460    },61    "summarization_xsum": {62      "length_penalty": 1.0,63      "max_length": 62,64      "min_length": 11,65      "num_beams": 666    }67  },68  "torch_dtype": "float32",69  "transformers_version": "4.27.3",70  "use_cache": true,71  "vocab_size": 5026572}73