nemoonyte/stack-bert-model

1{2  "add_cross_attention": false,3  "architectures": [4    "BertForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": null,8  "classifier_dropout": null,9  "dtype": "float32",10  "eos_token_id": null,11  "gradient_checkpointing": false,12  "hidden_act": "gelu",13  "hidden_dropout_prob": 0.1,14  "hidden_size": 768,15  "id2label": {16    "0": "LABEL_0",17    "1": "LABEL_1",18    "2": "LABEL_2"19  },20  "initializer_range": 0.02,21  "intermediate_size": 3072,22  "is_decoder": false,23  "label2id": {24    "LABEL_0": 0,25    "LABEL_1": 1,26    "LABEL_2": 227  },28  "layer_norm_eps": 1e-12,29  "max_position_embeddings": 512,30  "model_type": "bert",31  "num_attention_heads": 12,32  "num_hidden_layers": 12,33  "pad_token_id": 0,34  "position_embedding_type": "absolute",35  "problem_type": "single_label_classification",36  "tie_word_embeddings": true,37  "transformers_version": "5.4.0",38  "type_vocab_size": 2,39  "use_cache": true,40  "vocab_size": 3052241}42