djsull/binary_classification

1{2  "_name_or_path": "klue/roberta-small",3  "architectures": [4    "RobertaForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": 0,8  "classifier_dropout": null,9  "eos_token_id": 2,10  "gradient_checkpointing": false,11  "hidden_act": "gelu",12  "hidden_dropout_prob": 0.1,13  "hidden_size": 768,14  "id2label": {15    "0": "None",16    "1": "Profile"17  },18  "initializer_range": 0.02,19  "intermediate_size": 3072,20  "label2id": {21    "None": 0,22    "Profile": 123  },24  "layer_norm_eps": 1e-05,25  "max_position_embeddings": 514,26  "model_type": "roberta",27  "num_attention_heads": 12,28  "num_hidden_layers": 6,29  "pad_token_id": 1,30  "position_embedding_type": "absolute",31  "problem_type": "single_label_classification",32  "tokenizer_class": "BertTokenizer",33  "torch_dtype": "float32",34  "transformers_version": "4.40.2",35  "type_vocab_size": 1,36  "use_cache": true,37  "vocab_size": 3200038}39