Upload 6 files
Browse files- config.json +50 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"id2label": {
|
14 |
+
"0": "\u0440\u0430\u0434\u043e\u0441\u0442\u044c",
|
15 |
+
"1": "\u0438\u043d\u0442\u0435\u0440\u0435\u0441",
|
16 |
+
"2": "\u0443\u0434\u0438\u0432\u043b\u0435\u043d\u0438\u0435",
|
17 |
+
"3": "\u043f\u0435\u0447\u0430\u043b\u044c",
|
18 |
+
"4": "\u0433\u043d\u0435\u0432",
|
19 |
+
"5": "\u043e\u0442\u0432\u0440\u0430\u0449\u0435\u043d\u0438\u0435",
|
20 |
+
"6": "\u0441\u0442\u0440\u0430\u0445",
|
21 |
+
"7": "\u0432\u0438\u043d\u0430",
|
22 |
+
"8": "\u043d\u0435\u0439\u0442\u0440\u0430\u043b\u044c\u043d\u043e"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 600,
|
26 |
+
"label2id": {
|
27 |
+
"\u0432\u0438\u043d\u0430": 7,
|
28 |
+
"\u0433\u043d\u0435\u0432": 4,
|
29 |
+
"\u0438\u043d\u0442\u0435\u0440\u0435\u0441": 1,
|
30 |
+
"\u043d\u0435\u0439\u0442\u0440\u0430\u043b\u044c\u043d\u043e": 8,
|
31 |
+
"\u043e\u0442\u0432\u0440\u0430\u0449\u0435\u043d\u0438\u0435": 5,
|
32 |
+
"\u043f\u0435\u0447\u0430\u043b\u044c": 3,
|
33 |
+
"\u0440\u0430\u0434\u043e\u0441\u0442\u044c": 0,
|
34 |
+
"\u0441\u0442\u0440\u0430\u0445": 6,
|
35 |
+
"\u0443\u0434\u0438\u0432\u043b\u0435\u043d\u0438\u0435": 2
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"max_position_embeddings": 2048,
|
39 |
+
"model_type": "bert",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 3,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "multi_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.27.4",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 83828
|
50 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:294d672e8ad60d9432f90582aed8467791792be10cc80bbeac2284ad5839f9e3
|
3 |
+
size 116820959
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"never_split": null,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|