1 {
2 "_name_or_path": "DeepPavlov/rubert-base-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": 768,
13 "id2label": {
14 "0": "entailment",
15 "1": "contradiction",
16 "2": "neutral"
17 },
18 "initializer_range": 0.02,
19 "intermediate_size": 3072,
20 "label2id": {
21 "contradiction": 1,
22 "entailment": 0,
23 "neutral": 2
24 },
25 "layer_norm_eps": 1e-12,
26 "max_position_embeddings": 512,
27 "model_type": "bert",
28 "num_attention_heads": 12,
29 "num_hidden_layers": 12,
30 "output_past": true,
31 "pad_token_id": 0,
32 "pooler_fc_size": 768,
33 "pooler_num_attention_heads": 12,
34 "pooler_num_fc_layers": 3,
35 "pooler_size_per_head": 128,
36 "pooler_type": "first_token_transform",
37 "position_embedding_type": "absolute",
38 "problem_type": "single_label_classification",
39 "torch_dtype": "float32",
40 "transformers_version": "4.10.3",
41 "type_vocab_size": 2,
42 "use_cache": true,
43 "vocab_size": 119547
44 }
45