|
{ |
|
"_name_or_path": "ai-forever/ruBert-large", |
|
"architectures": [ |
|
"BertForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"directionality": "bidi", |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"id2label": { |
|
"0": "\u043b\u0435\u0433\u043a\u0438\u0439", |
|
"1": "\u0441\u043b\u043e\u0436\u043d\u044b\u0439", |
|
"2": "\u043e\u0447\u0435\u043d\u044c \u0441\u043b\u043e\u0436\u043d\u044b\u0439" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4096, |
|
"label2id": { |
|
"\u043b\u0435\u0433\u043a\u0438\u0439": 0, |
|
"\u043e\u0447\u0435\u043d\u044c \u0441\u043b\u043e\u0436\u043d\u044b\u0439": 2, |
|
"\u0441\u043b\u043e\u0436\u043d\u044b\u0439": 1 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 24, |
|
"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": false, |
|
"vocab_size": 120138 |
|
} |
|
|