CodeHima/TOSBert

1{2  "_name_or_path": "./tos-bert-classifier",3  "architectures": [4    "BertForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "classifier_dropout": null,8  "gradient_checkpointing": false,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "hidden_size": 768,12  "id2label": {13    "0": "LABEL_0",14    "1": "LABEL_1",15    "2": "LABEL_2",16    "3": "LABEL_3",17    "4": "LABEL_4",18    "5": "LABEL_5",19    "6": "LABEL_6",20    "7": "LABEL_7",21    "8": "LABEL_8"22  },23  "initializer_range": 0.02,24  "intermediate_size": 3072,25  "label2id": {26    "LABEL_0": 0,27    "LABEL_1": 1,28    "LABEL_2": 2,29    "LABEL_3": 3,30    "LABEL_4": 4,31    "LABEL_5": 5,32    "LABEL_6": 6,33    "LABEL_7": 7,34    "LABEL_8": 835  },36  "layer_norm_eps": 1e-12,37  "max_position_embeddings": 512,38  "model_type": "bert",39  "num_attention_heads": 12,40  "num_hidden_layers": 12,41  "pad_token_id": 0,42  "position_embedding_type": "absolute",43  "problem_type": "multi_label_classification",44  "torch_dtype": "float32",45  "transformers_version": "4.42.1",46  "type_vocab_size": 2,47  "use_cache": true,48  "vocab_size": 3052249}50