|
{ |
|
"_name_or_path": "../model/", |
|
"architectures": [ |
|
"DebertaV2ForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"id2label": { |
|
"0": "\u043e\u0442\u0435\u0446", |
|
"1": "\u043c\u0430\u0442\u044c", |
|
"2": "\u0440\u0435\u0431\u0435\u043d\u043e\u043a", |
|
"3": "\u0441\u0443\u043f\u0440\u0443\u0433", |
|
"4": "\u0431\u044b\u0432\u0448\u0438\u0439 \u0441\u0443\u043f\u0440\u0443\u0433", |
|
"5": "\u043e \u0441\u0435\u0431\u0435" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4096, |
|
"label2id": { |
|
"\u0431\u044b\u0432\u0448\u0438\u0439 \u0441\u0443\u043f\u0440\u0443\u0433": 4, |
|
"\u043c\u0430\u0442\u044c": 1, |
|
"\u043e \u0441\u0435\u0431\u0435": 5, |
|
"\u043e\u0442\u0435\u0446": 0, |
|
"\u0440\u0435\u0431\u0435\u043d\u043e\u043a": 2, |
|
"\u0441\u0443\u043f\u0440\u0443\u0433": 3 |
|
}, |
|
"layer_norm_eps": 1e-07, |
|
"legacy": true, |
|
"max_position_embeddings": 512, |
|
"max_relative_positions": -1, |
|
"model_type": "deberta-v2", |
|
"norm_rel_ebd": "layer_norm", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 24, |
|
"pad_token_id": 0, |
|
"pooler_dropout": 0, |
|
"pooler_hidden_act": "gelu", |
|
"pooler_hidden_size": 1024, |
|
"pos_att_type": [ |
|
"p2c", |
|
"c2p" |
|
], |
|
"position_biased_input": false, |
|
"position_buckets": 256, |
|
"relative_attention": true, |
|
"share_att_key": true, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.47.0", |
|
"type_vocab_size": 0, |
|
"vocab_size": 128100 |
|
} |
|
|