ModelTC/bart-base-cnn

1{2  "activation_dropout": 0.1,3  "activation_function": "gelu",4  "add_bias_logits": false,5  "add_final_layer_norm": false,6  "architectures": [7    "BartModel",8    "BartForConditionalGeneration",9    "BartForSequenceClassification"10  ],11  "attention_dropout": 0.1,12  "bos_token_id": 0,13  "classif_dropout": 0.1,14  "d_model": 768,15  "decoder_attention_heads": 12,16  "decoder_ffn_dim": 3072,17  "decoder_layerdrop": 0.0,18  "decoder_layers": 6,19  "decoder_start_token_id": 2,20  "dropout": 0.1,21  "early_stopping": true,22  "encoder_attention_heads": 12,23  "encoder_ffn_dim": 3072,24  "encoder_layerdrop": 0.0,25  "encoder_layers": 6,26  "eos_token_id": 2,27  "id2label": {28    "0": "LABEL_0",29    "1": "LABEL_1",30    "2": "LABEL_2"31  },32  "init_std": 0.02,33  "is_encoder_decoder": true,34  "label2id": {35    "LABEL_0": 0,36    "LABEL_1": 1,37    "LABEL_2": 238  },39  "max_position_embeddings": 1024,40  "model_type": "bart",41  "normalize_before": false,42  "normalize_embedding": true,43  "num_hidden_layers": 6,44  "pad_token_id": 1,45  "scale_embedding": false,46  "num_beams": 4,47  "no_repeat_ngram_size": 3,48  "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  "vocab_size": 5026569}70