presuisidal_model / config.json
astromis's picture
Upload BertForSequenceClassification
e658982 verified
{
"_name_or_path": "/workspace/model_outputs_test/presui-label_exact_15-mapping_prior_label_v0/best_model/",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10",
"11": "LABEL_11",
"12": "LABEL_12",
"13": "LABEL_13",
"14": "LABEL_14"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"\u0414\u0435\u0441\u0442\u0440\u0443\u043a\u0442\u0438\u0432\u043d\u043e\u0435 \u043f\u043e\u0432\u0435\u0434\u0435\u043d\u0438\u0435/\u0430\u043b\u043a\u043e\u0433\u043e\u043b\u044c \u0438 \u043d\u0430\u0440\u043a\u043e\u0442\u0438\u043a\u0438": 0,
"\u0414\u0435\u0441\u0442\u0440\u0443\u043a\u0442\u0438\u0432\u043d\u043e\u0435 \u043f\u043e\u0432\u0435\u0434\u0435\u043d\u0438\u0435/\u0441\u0430\u043c\u043e\u043f\u043e\u0432\u0440\u0435\u0436\u0434\u0435\u043d\u0438\u0435": 1,
"\u0414\u0440\u0443\u0433\u043e\u0435": 2,
"\u0417\u0430\u0449\u0438\u0442\u043d\u044b\u0435 \u0444\u0430\u043a\u0442\u043e\u0440\u044b": 3,
"\u041a\u043b\u0438\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u044f\u0432\u043b\u0435\u043d\u0438\u044f": 4,
"\u041a\u043b\u0438\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u044f\u0432\u043b\u0435\u043d\u0438\u044f/\u0434\u0435\u043f\u0440\u0435\u0441\u0441\u0438\u044f": 5,
"\u041a\u043b\u0438\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u044f\u0432\u043b\u0435\u043d\u0438\u044f/\u043f\u043b\u0430\u0447, \u0438\u0441\u0442\u0435\u0440\u0438\u043a\u0438": 6,
"\u041a\u043b\u0438\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u044f\u0432\u043b\u0435\u043d\u0438\u044f/\u043f\u043e\u043f\u044b\u0442\u043a\u0430 \u0441\u0443\u0438\u0446\u0438\u0434\u0430 \u0432 \u043f\u0440\u043e\u0448\u043b\u043e\u043c": 7,
"\u041d\u0435\u0440\u0435\u043b\u0435\u0432\u0430\u043d\u0442\u043d\u044b\u0439": 8,
"\u041f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u0432 \u0441\u0435\u043c\u044c\u0435": 9,
"\u041f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u0432\u043e \u0432\u043d\u0435\u0448\u043d\u0435\u043c \u043c\u0438\u0440\u0435/\u043d\u0435\u0441\u0447\u0430\u0441\u0442\u043d\u0430\u044f \u043b\u044e\u0431\u043e\u0432\u044c, \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u0441 \u0434\u0440\u0443\u0437\u044c\u044f\u043c\u0438, \u0441\u043b\u043e\u0436\u043d\u043e\u0441\u0442\u0438 \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043e\u0442\u043d\u043e\u0448\u0435\u043d\u0438\u0439 \u0438 \u0427\u0443\u0432\u0441\u0442\u0432\u0430/\u043e\u0434\u0438\u043d\u043e\u0447\u0435\u0441\u0442\u0432\u043e, \u043d\u0435\u043f\u043e\u043d\u0438\u043c\u0430\u043d\u0438\u0435, \u0438\u0437\u043e\u043b\u044f\u0446\u0438\u044f, \u0431\u0440\u043e\u0448\u0435\u043d\u043d\u043e\u0441\u0442\u044c": 10,
"\u0421\u043c\u0435\u0440\u0442\u044c/\u043c\u044b\u0441\u043b\u0438 \u043e \u0441\u043c\u0435\u0440\u0442\u0438 \u0438 \u043d\u0430\u043c\u0435\u0440\u0435\u043d\u0438\u044f \u0441\u0430\u043c\u043e\u0443\u0431\u0438\u0439\u0441\u0442\u0432\u0430": 11,
"\u0421\u043c\u0435\u0440\u0442\u044c/\u0441\u043c\u0435\u0440\u0442\u044c, \u043d\u0435\u0441\u0447\u0430\u0441\u0442\u043d\u044b\u0439 \u0441\u043b\u0443\u0447\u0430\u0439 \u0438\u043b\u0438 \u0441\u0443\u0438\u0446\u0438\u0434 \u0431\u043b\u0438\u0437\u043a\u0438\u0445": 12,
"\u0427\u0443\u0432\u0441\u0442\u0432\u0430": 13,
"\u0444\u0438\u0437\u0438\u0447\u0435\u0441\u043a\u043e\u0435 \u0438 \u0441\u0435\u043a\u0441\u0443\u0430\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u043e\u0435 \u043d\u0430\u0441\u0438\u043b\u0438\u0435, \u0442\u0440\u0430\u0432\u043b\u044f": 14
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}