CoolFace
Modelpublic

cppmai/finetune_bart-base_classification

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes7downloads
config.json103 linesDownload Raw Back to root
1{2  "_name_or_path": "/gpfs/home/pchau/intern-text-summarization/pretrain_bart/finetune-classification/output_bart-base",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": 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  "forced_bos_token_id": 0,28  "forced_eos_token_id": 2,29  "gradient_checkpointing": false,30  "id2label": {31    "0": "advertisement",32    "1": "budget",33    "2": "email",34    "3": "file_folder",35    "4": "form",36    "5": "handwritten",37    "6": "invoice",38    "7": "letter",39    "8": "memo",40    "9": "news_article",41    "10": "presentation",42    "11": "publication",43    "12": "questionnaire",44    "13": "report",45    "14": "resume",46    "15": "specification"47  },48  "init_std": 0.02,49  "is_encoder_decoder": true,50  "label2id": {51    "advertisement": 0,52    "budget": 1,53    "email": 2,54    "file_folder": 3,55    "form": 4,56    "handwritten": 5,57    "invoice": 6,58    "letter": 7,59    "memo": 8,60    "news_article": 9,61    "presentation": 10,62    "publication": 11,63    "questionnaire": 12,64    "report": 13,65    "resume": 14,66    "specification": 1567  },68  "max_position_embeddings": 1024,69  "model_type": "bart",70  "no_repeat_ngram_size": 3,71  "normalize_before": false,72  "normalize_embedding": true,73  "num_beams": 4,74  "num_hidden_layers": 6,75  "pad_token_id": 1,76  "problem_type": "single_label_classification",77  "scale_embedding": false,78  "task_specific_params": {79    "summarization": {80      "length_penalty": 1.0,81      "max_length": 128,82      "min_length": 12,83      "num_beams": 484    },85    "summarization_cnn": {86      "length_penalty": 2.0,87      "max_length": 142,88      "min_length": 56,89      "num_beams": 490    },91    "summarization_xsum": {92      "length_penalty": 1.0,93      "max_length": 62,94      "min_length": 11,95      "num_beams": 696    }97  },98  "torch_dtype": "float32",99  "transformers_version": "4.41.2",100  "use_cache": true,101  "vocab_size": 50265102}103