aieng-lab/bert-large-cased_comment-type-java

1{2  "_name_or_path": "bert-large-cased",3  "architectures": [4    "BertForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "classifier_dropout": null,8  "directionality": "bidi",9  "gradient_checkpointing": false,10  "hidden_act": "gelu",11  "hidden_dropout_prob": 0.1,12  "hidden_size": 1024,13  "id2label": {14    "0": "LABEL_0",15    "1": "LABEL_1",16    "2": "LABEL_2",17    "3": "LABEL_3",18    "4": "LABEL_4",19    "5": "LABEL_5",20    "6": "LABEL_6"21  },22  "initializer_range": 0.02,23  "intermediate_size": 4096,24  "label2id": {25    "LABEL_0": 0,26    "LABEL_1": 1,27    "LABEL_2": 2,28    "LABEL_3": 3,29    "LABEL_4": 4,30    "LABEL_5": 5,31    "LABEL_6": 632  },33  "layer_norm_eps": 1e-12,34  "max_position_embeddings": 512,35  "model_type": "bert",36  "num_attention_heads": 16,37  "num_hidden_layers": 24,38  "pad_token_id": 0,39  "pooler_fc_size": 768,40  "pooler_num_attention_heads": 12,41  "pooler_num_fc_layers": 3,42  "pooler_size_per_head": 128,43  "pooler_type": "first_token_transform",44  "position_embedding_type": "absolute",45  "problem_type": "multi_label_classification",46  "torch_dtype": "bfloat16",47  "transformers_version": "4.48.3",48  "type_vocab_size": 2,49  "use_cache": true,50  "vocab_size": 2899651}52