|
{ |
|
"_name_or_path": "cointegrated/rubert-tiny2", |
|
"architectures": [ |
|
"BertForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"emb_size": 312, |
|
"gradient_checkpointing": false, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 312, |
|
"id2label": { |
|
"0": "\u0440\u0430\u0434\u043e\u0441\u0442\u044c", |
|
"1": "\u0438\u043d\u0442\u0435\u0440\u0435\u0441", |
|
"2": "\u0443\u0434\u0438\u0432\u043b\u0435\u043d\u0438\u0435", |
|
"3": "\u043f\u0435\u0447\u0430\u043b\u044c", |
|
"4": "\u0433\u043d\u0435\u0432", |
|
"5": "\u043e\u0442\u0432\u0440\u0430\u0449\u0435\u043d\u0438\u0435", |
|
"6": "\u0441\u0442\u0440\u0430\u0445", |
|
"7": "\u0432\u0438\u043d\u0430", |
|
"8": "\u043d\u0435\u0439\u0442\u0440\u0430\u043b\u044c\u043d\u043e" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 600, |
|
"label2id": { |
|
"\u0432\u0438\u043d\u0430": 7, |
|
"\u0433\u043d\u0435\u0432": 4, |
|
"\u0438\u043d\u0442\u0435\u0440\u0435\u0441": 1, |
|
"\u043d\u0435\u0439\u0442\u0440\u0430\u043b\u044c\u043d\u043e": 8, |
|
"\u043e\u0442\u0432\u0440\u0430\u0449\u0435\u043d\u0438\u0435": 5, |
|
"\u043f\u0435\u0447\u0430\u043b\u044c": 3, |
|
"\u0440\u0430\u0434\u043e\u0441\u0442\u044c": 0, |
|
"\u0441\u0442\u0440\u0430\u0445": 6, |
|
"\u0443\u0434\u0438\u0432\u043b\u0435\u043d\u0438\u0435": 2 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 2048, |
|
"model_type": "bert", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 3, |
|
"pad_token_id": 0, |
|
"position_embedding_type": "absolute", |
|
"problem_type": "multi_label_classification", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.27.4", |
|
"type_vocab_size": 2, |
|
"use_cache": true, |
|
"vocab_size": 83828 |
|
} |
|
|