|
{ |
|
"_name_or_path": "ai-forever/ruBert-base", |
|
"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", |
|
"15": "LABEL_15", |
|
"16": "LABEL_16", |
|
"17": "LABEL_17", |
|
"18": "LABEL_18", |
|
"19": "LABEL_19" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_10": 10, |
|
"LABEL_11": 11, |
|
"LABEL_12": 12, |
|
"LABEL_13": 13, |
|
"LABEL_14": 14, |
|
"LABEL_15": 15, |
|
"LABEL_16": 16, |
|
"LABEL_17": 17, |
|
"LABEL_18": 18, |
|
"LABEL_19": 19, |
|
"LABEL_2": 2, |
|
"LABEL_3": 3, |
|
"LABEL_4": 4, |
|
"LABEL_5": 5, |
|
"LABEL_6": 6, |
|
"LABEL_7": 7, |
|
"LABEL_8": 8, |
|
"LABEL_9": 9 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"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": "4.41.2", |
|
"type_vocab_size": 2, |
|
"use_cache": true, |
|
"vocab_size": 120138 |
|
} |
|
|