Hugging Face's logo

ruaccent
/
accentuator

ONNX
Russian
Model card Files
xet
Community
1
Den4ikAI commited on
Commit
20a943f
·
verified ·
1 Parent(s): 94e7023

Delete nn

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. nn/nn_accent/config.json +0 -37
  2. nn/nn_accent/model.onnx +0 -3
  3. nn/nn_accent/no_quant.onnx +0 -3
  4. nn/nn_accent/ort_config.json +0 -30
  5. nn/nn_accent/special_tokens_map.json +0 -6
  6. nn/nn_accent/tokenizer_config.json +0 -10
  7. nn/nn_accent/vocab.txt +0 -45
  8. nn/nn_morph/morph/config.json +0 -66
  9. nn/nn_morph/morph/model.onnx +0 -3
  10. nn/nn_morph/morph/special_tokens_map.json +0 -7
  11. nn/nn_morph/morph/tokenizer.json +0 -0
  12. nn/nn_morph/morph/tokenizer_config.json +0 -15
  13. nn/nn_morph/morph/vocab.txt +0 -0
  14. nn/nn_morph/syntax/added_tokens.json +0 -18
  15. nn/nn_morph/syntax/config.json +0 -436
  16. nn/nn_morph/syntax/model.onnx +0 -3
  17. nn/nn_morph/syntax/special_tokens_map.json +0 -7
  18. nn/nn_morph/syntax/tokenizer.json +0 -0
  19. nn/nn_morph/syntax/tokenizer_config.json +0 -15
  20. nn/nn_morph/syntax/vocab.txt +0 -0
  21. nn/nn_omograph/big/added_tokens.json +0 -4
  22. nn/nn_omograph/big/config.json +0 -31
  23. nn/nn_omograph/big/model.onnx +0 -3
  24. nn/nn_omograph/big/special_tokens_map.json +0 -7
  25. nn/nn_omograph/big/tokenizer.json +0 -0
  26. nn/nn_omograph/big/tokenizer_config.json +0 -15
  27. nn/nn_omograph/big/vocab.txt +0 -0
  28. nn/nn_omograph/big_poetry/added_tokens.json +0 -4
  29. nn/nn_omograph/big_poetry/config.json +0 -31
  30. nn/nn_omograph/big_poetry/model.onnx +0 -3
  31. nn/nn_omograph/big_poetry/special_tokens_map.json +0 -7
  32. nn/nn_omograph/big_poetry/tokenizer.json +0 -0
  33. nn/nn_omograph/big_poetry/tokenizer_config.json +0 -15
  34. nn/nn_omograph/big_poetry/vocab.txt +0 -0
  35. nn/nn_omograph/medium/added_tokens.json +0 -4
  36. nn/nn_omograph/medium/config.json +0 -31
  37. nn/nn_omograph/medium/model.onnx +0 -3
  38. nn/nn_omograph/medium/special_tokens_map.json +0 -7
  39. nn/nn_omograph/medium/tokenizer.json +0 -0
  40. nn/nn_omograph/medium/tokenizer_config.json +0 -15
  41. nn/nn_omograph/medium/vocab.txt +0 -0
  42. nn/nn_omograph/medium_poetry/added_tokens.json +0 -4
  43. nn/nn_omograph/medium_poetry/config.json +0 -31
  44. nn/nn_omograph/medium_poetry/model.onnx +0 -3
  45. nn/nn_omograph/medium_poetry/special_tokens_map.json +0 -7
  46. nn/nn_omograph/medium_poetry/tokenizer.json +0 -0
  47. nn/nn_omograph/medium_poetry/tokenizer_config.json +0 -15
  48. nn/nn_omograph/medium_poetry/vocab.txt +0 -0
  49. nn/nn_omograph/small/added_tokens.json +0 -4
  50. nn/nn_omograph/small/config.json +0 -27
nn/nn_accent/config.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "_name_or_path": "onnx_out",
3
- "architectures": [
4
- "DLMForTokenClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.2,
7
- "embedding_size": 128,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.2,
10
- "hidden_size": 128,
11
- "id2label": {
12
- "0": "NO",
13
- "1": "STRESS_PRIMARY",
14
- "2": "STRESS_SECONDARY"
15
- },
16
- "initializer_range": 0.02,
17
- "intermediate_size": 256,
18
- "label2id": {
19
- "NO": 0,
20
- "STRESS_PRIMARY": 1,
21
- "STRESS_SECONDARY": 2
22
- },
23
- "layer_norm_eps": 1e-12,
24
- "max_length": 40,
25
- "max_position_embeddings": 60,
26
- "max_relative_positions": 60,
27
- "model_type": "dlm",
28
- "num_attention_heads": 8,
29
- "num_hidden_layers": 4,
30
- "pad_token_id": 0,
31
- "relative_attention": true,
32
- "rotary_value": false,
33
- "transformers_version": "4.29.2",
34
- "type_vocab_size": 2,
35
- "use_cache": true,
36
- "vocab_size": 45
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_accent/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e393144e45626f6f1062a0784ef06f921b97321a8e7b87ac2a09a892286500a
3
- size 803402
 
 
 
 
nn/nn_accent/no_quant.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:47e69d9ae19f2a82e21b1c70f6a4bbfb1abc5759e98b2e67d009c5e9d7af18c9
3
- size 2285217
 
 
 
 
nn/nn_accent/ort_config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "one_external_file": true,
3
- "opset": null,
4
- "optimization": {},
5
- "optimum_version": "1.8.5",
6
- "quantization": {
7
- "activations_dtype": "QUInt8",
8
- "activations_symmetric": false,
9
- "format": "QOperator",
10
- "is_static": false,
11
- "mode": "IntegerOps",
12
- "nodes_to_exclude": [],
13
- "nodes_to_quantize": [],
14
- "operators_to_quantize": [
15
- "MatMul",
16
- "Add"
17
- ],
18
- "per_channel": false,
19
- "qdq_add_pair_to_weight": false,
20
- "qdq_dedicated_pair": false,
21
- "qdq_op_type_per_channel_support_to_axis": {
22
- "MatMul": 1
23
- },
24
- "reduce_range": false,
25
- "weights_dtype": "QInt8",
26
- "weights_symmetric": true
27
- },
28
- "transformers_version": "4.29.2",
29
- "use_external_data_format": false
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_accent/special_tokens_map.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "bos_token": "[bos]",
3
- "eos_token": "[eos]",
4
- "pad_token": "[pad]",
5
- "unk_token": "[unk]"
6
- }
 
 
 
 
 
 
 
nn/nn_accent/tokenizer_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "bos_token": "[bos]",
3
- "clean_up_tokenization_spaces": true,
4
- "do_lower_case": true,
5
- "eos_token": "[eos]",
6
- "model_max_length": 1000000000000000019884624838656,
7
- "pad_token": "[pad]",
8
- "tokenizer_class": "CharTokenizer",
9
- "unk_token": "[unk]"
10
- }
 
 
 
 
 
 
 
 
 
 
 
nn/nn_accent/vocab.txt DELETED
@@ -1,45 +0,0 @@
1
- [pad]
2
- [unk]
3
- [bos]
4
- [eos]
5
- '
6
- -
7
- .
8
- ?
9
- `
10
- c
11
- e
12
- ́
13
- а
14
- б
15
- в
16
- г
17
- д
18
- е
19
- ж
20
- з
21
- и
22
- й
23
- к
24
- л
25
- м
26
- н
27
- о
28
- п
29
- р
30
- с
31
- т
32
- у
33
- ф
34
- х
35
- ц
36
- ч
37
- ш
38
- щ
39
- ъ
40
- ы
41
- ь
42
- э
43
- ю
44
- я
45
- ё
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_morph/morph/config.json DELETED
@@ -1,66 +0,0 @@
1
- {
2
- "_name_or_path": "5k",
3
- "architectures": [
4
- "BertForTokenClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "id2label": {
13
- "0": "H",
14
- "1": "X",
15
- "2": "PRON",
16
- "3": "LATN",
17
- "4": "ADJ",
18
- "5": "INTJ",
19
- "6": "SYM",
20
- "7": "VERB",
21
- "8": "DET",
22
- "9": "CONJ",
23
- "10": "PART",
24
- "11": "NUM",
25
- "12": "NOUN",
26
- "13": "PUNCT",
27
- "14": "ADV",
28
- "15": "ADP"
29
- },
30
- "initializer_range": 0.02,
31
- "intermediate_size": 3072,
32
- "label2id": {
33
- "ADJ": 4,
34
- "ADP": 15,
35
- "ADV": 14,
36
- "CONJ": 9,
37
- "DET": 8,
38
- "H": 0,
39
- "INTJ": 5,
40
- "LATN": 3,
41
- "NOUN": 12,
42
- "NUM": 11,
43
- "PART": 10,
44
- "PRON": 2,
45
- "PUNCT": 13,
46
- "SYM": 6,
47
- "VERB": 7,
48
- "X": 1
49
- },
50
- "layer_norm_eps": 1e-12,
51
- "max_position_embeddings": 512,
52
- "model_type": "bert",
53
- "num_attention_heads": 12,
54
- "num_hidden_layers": 12,
55
- "pad_token_id": 0,
56
- "pooler_fc_size": 768,
57
- "pooler_num_attention_heads": 12,
58
- "pooler_num_fc_layers": 3,
59
- "pooler_size_per_head": 128,
60
- "pooler_type": "first_token_transform",
61
- "position_embedding_type": "absolute",
62
- "transformers_version": "4.29.2",
63
- "type_vocab_size": 2,
64
- "use_cache": true,
65
- "vocab_size": 120138
66
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_morph/morph/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be0c75e02eac6da05f1e50f1c296785bef9a7e9bf28bd57aedca4c483598009d
3
- size 711182365
 
 
 
 
nn/nn_morph/morph/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
nn/nn_morph/morph/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_morph/morph/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_morph/morph/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_morph/syntax/added_tokens.json DELETED
@@ -1,18 +0,0 @@
1
- {
2
- "=ADJ": 120142,
3
- "=ADP": 120153,
4
- "=ADV": 120152,
5
- "=CONJ": 120147,
6
- "=DET": 120146,
7
- "=H": 120138,
8
- "=INTJ": 120143,
9
- "=LATN": 120141,
10
- "=NOUN": 120150,
11
- "=NUM": 120149,
12
- "=PART": 120148,
13
- "=PRON": 120140,
14
- "=PUNCT": 120151,
15
- "=SYM": 120144,
16
- "=VERB": 120145,
17
- "=X": 120139
18
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_morph/syntax/config.json DELETED
@@ -1,436 +0,0 @@
1
- {
2
- "_name_or_path": "base/",
3
- "architectures": [
4
- "BertForTokenClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "id2label": {
13
- "0": "Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
14
- "1": "Mood=Ind|Number=Sing|Person=2|Tense=Pres|VerbForm=Fin",
15
- "2": "Case=Acc|Gender=Masc|Number=Sing|Person=3",
16
- "3": "Case=Ins|Degree=Pos|Gender=Neut|Number=Plur",
17
- "4": "Degree=Pos|Number=Sing|Variant=Short",
18
- "5": "Case=Dat|Degree=Cmp|Gender=Neut|Number=Sing",
19
- "6": "Case=Gen|Number=Sing|Person=2",
20
- "7": "Case=Nom|Gender=Neut|Number=Plur",
21
- "8": "Case=Loc|Degree=Pos|Gender=Masc|Number=Sing",
22
- "9": "Case=Nom|Gender=Neut",
23
- "10": "Case=Ins|Number=Sing|Person=2",
24
- "11": "Case=Gen",
25
- "12": "Mood=Ind|Tense=Pres|VerbForm=Fin",
26
- "13": "Case=Acc|Number=Sing|Person=2",
27
- "14": "Case=Gen|Degree=Cmp|Gender=Neut|Number=Sing",
28
- "15": "Case=Loc|Number=Sing|Person=1",
29
- "16": "Case=Gen|Degree=Pos|Gender=Masc|Number=Plur",
30
- "17": "Mood=Ind|Number=Sing|Person=3|Tense=Fut|VerbForm=Fin",
31
- "18": "Case=Dat|Gender=Masc",
32
- "19": "Case=Ins|Gender=Masc|Number=Sing",
33
- "20": "Case=Acc|Degree=Pos|Gender=Neut|Number=Sing",
34
- "21": "Mood=Imp|Number=Plur|Person=1|VerbForm=Fin",
35
- "22": "Case=Dat|Degree=Pos|Gender=Fem|Number=Sing",
36
- "23": "Case=Acc|Number=Plur|Person=3",
37
- "24": "Case=Gen|Number=Plur|Person=1",
38
- "25": "Mood=Ind|Number=Plur|Person=2|Tense=Pres|VerbForm=Fin",
39
- "26": "Case=Dat|Gender=Neut",
40
- "27": "Mood=Ind|Number=Plur|Person=3|Tense=Notpast|VerbForm=Fin",
41
- "28": "Mood=Ind|Number=Plur|Person=1|Tense=Notpast|VerbForm=Fin",
42
- "29": "Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin",
43
- "30": "Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin",
44
- "31": "Case=Nom|Number=Sing|Person=2",
45
- "32": "Case=Voc|Gender=Fem|Number=Sing",
46
- "33": "Case=Loc|Number=Plur|Person=2",
47
- "34": "Case=Dat|Number=Plur",
48
- "35": "Case=Ins|Gender=Neut|Number=Sing",
49
- "36": "Degree=Pos|Gender=Fem|Number=Sing|Variant=Short",
50
- "37": "Case=Gen|Gender=Masc|Number=Sing|Person=3",
51
- "38": "Case=Gen|Gender=Masc|Number=Sing",
52
- "39": "Case=Acc|Degree=Cmp|Gender=Masc|Number=Sing",
53
- "40": "Mood=Ind|Number=Plur|Tense=Pres|VerbForm=Fin",
54
- "41": "Case=Ins|Number=Sing",
55
- "42": "Case=Nom|Number=Plur",
56
- "43": "Case=Gen|Degree=Pos|Number=Plur",
57
- "44": "Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin",
58
- "45": "Case=Nom|Gender=Fem|Number=Sing",
59
- "46": "Case=Acc|Number=Sing|Person=3",
60
- "47": "Case=Acc|Gender=Fem|Number=Sing",
61
- "48": "Case=Loc|Degree=Pos|Gender=Neut|Number=Sing",
62
- "49": "Case=Dat|Number=Plur|Person=1",
63
- "50": "Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin",
64
- "51": "Case=Nom|Degree=Pos|Gender=Masc|Number=Sing|Variant=Short",
65
- "52": "Case=Dat|Degree=Cmp|Gender=Fem|Number=Sing",
66
- "53": "Mood=Ind|Number=Plur|Person=1|Tense=Fut|VerbForm=Fin",
67
- "54": "Case=Loc",
68
- "55": "Case=Acc|Gender=Neut|Number=Plur",
69
- "56": "Case=Nom|Degree=Cmp|Gender=Masc|Number=Sing",
70
- "57": "Degree=Pos|Gender=Fem|Number=Sing",
71
- "58": "Case=Gen|Gender=Fem|Number=Sing|Person=3",
72
- "59": "Case=Gen|Number=Plur|Number=Sing",
73
- "60": "Case=Loc|Gender=Masc",
74
- "61": "Case=Dat|Number=Plur|Person=2",
75
- "62": "Case=Ins|Degree=Cmp|Gender=Fem|Number=Sing",
76
- "63": "Case=Gen|Degree=Pos|Gender=Masc|Number=Sing",
77
- "64": "Case=Loc|Gender=Masc|Number=Sing|Person=3",
78
- "65": "Mood=Ind|Number=Plur|Person=2|Tense=Notpast|VerbForm=Fin",
79
- "66": "Case=Gen|Degree=Pos|Gender=Masc",
80
- "67": "Case=Acc|Degree=Cmp|Gender=Neut|Number=Sing",
81
- "68": "Case=Acc|Degree=Pos|Gender=Fem|Number=Sing",
82
- "69": "Case=Ins|Gender=Masc",
83
- "70": "Case=Dat|Degree=Pos|Gender=Masc|Number=Plur",
84
- "71": "Case=Nom|Degree=Pos|Number=Plur",
85
- "72": "Case=Gen|Number=Sing|Person=1",
86
- "73": "Case=Gen|Number=Plur|Person=3",
87
- "74": "Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin",
88
- "75": "Case=Dat|Gender=Neut|Number=Sing|Person=3",
89
- "76": "Case=Loc|Degree=Cmp|Gender=Masc|Number=Sing",
90
- "77": "Case=Nom|Gender=Fem|Number=Sing|Person=3",
91
- "78": "Case=Dat|Number=Sing",
92
- "79": "Case=Nom|Gender=Masc|Number=Plur",
93
- "80": "Case=Acc|Gender=Neut|Number=Sing",
94
- "81": "Case=Nom|Number=Plur|Person=2",
95
- "82": "Case=Ins",
96
- "83": "Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
97
- "84": "Case=Nom|Number=Plur|Person=3",
98
- "85": "Mood=Ind|Number=Sing|Person=3|Tense=Notpast|VerbForm=Fin",
99
- "86": "Case=Loc|Gender=Neut|Number=Sing|Person=3",
100
- "87": "Mood=Ind|Tense=Notpast|VerbForm=Fin",
101
- "88": "Mood=Ind|Number=Sing|Person=2|Tense=Fut|VerbForm=Fin",
102
- "89": "Case=Loc|Degree=Pos|Gender=Fem|Number=Sing",
103
- "90": "Mood=Ind|Number=Sing|Tense=Pres|VerbForm=Fin",
104
- "91": "Mood=Ind|Number=Plur|Person=2|Tense=Fut|VerbForm=Fin",
105
- "92": "Case=Ins|Degree=Pos|Gender=Fem|Number=Sing",
106
- "93": "Case=Ins|Degree=Pos|Gender=Neut|Number=Sing",
107
- "94": "Case=Ins|Gender=Fem|Number=Sing|Person=3",
108
- "95": "Case=Loc|Degree=Cmp|Gender=Neut|Number=Sing",
109
- "96": "Case=Loc|Number=Plur",
110
- "97": "_",
111
- "98": "Case=Acc|Gender=Neut|Number=Sing|Person=3",
112
- "99": "Case=Nom|Number=Sing",
113
- "100": "Case=Ins|Gender=Masc|Number=Sing|Person=3",
114
- "101": "Case=Acc|Degree=Pos|Number=Plur",
115
- "102": "Case=Gen|Number=Sing",
116
- "103": "Case=Loc|Gender=Fem|Number=Sing",
117
- "104": "Case=Dat|Degree=Pos|Number=Plur",
118
- "105": "Case=Nom|Gender=Neut|Number=Sing",
119
- "106": "VerbForm=Conv",
120
- "107": "Degree=Pos|Gender=Neut|Number=Sing|Variant=Short",
121
- "108": "Case=Nom|Gender=Masc|Number=Sing|Person=3",
122
- "109": "VerbForm=Inf",
123
- "110": "Case=Dat|Gender=Masc|Number=Sing|Person=3",
124
- "111": "Case=Dat|Gender=Neut|Number=Sing",
125
- "112": "Mood=Ind|Number=Sing|Person=1|Tense=Notpast|VerbForm=Fin",
126
- "113": "Case=Nom|Gender=Masc",
127
- "114": "Case=Acc|Gender=Fem|Number=Sing|Person=3",
128
- "115": "Mood=Ind|Tense=Fut|VerbForm=Fin",
129
- "116": "Case=Nom",
130
- "117": "Mood=Ind|Number=Sing|Person=2|Tense=Notpast|VerbForm=Fin",
131
- "118": "Case=Nom|Degree=Pos|Gender=Neut|Number=Plur",
132
- "119": "Case=Nom|Gender=Neut|Number=Sing|Person=3",
133
- "120": "Case=Dat|Gender=Fem|Number=Sing|Person=3",
134
- "121": "Case=Gen|Gender=Fem|Number=Sing",
135
- "122": "Case=Gen|Degree=Pos|Gender=Fem|Number=Sing",
136
- "123": "Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin",
137
- "124": "Case=Dat|Degree=Pos|Gender=Masc|Number=Sing",
138
- "125": "Case=Ins|Degree=Pos|Gender=Masc|Number=Sing",
139
- "126": "Case=Nom|Number=Plur|Number=Sing",
140
- "127": "Case=Acc|Number=Plur",
141
- "128": "Case=Acc|Degree=Cmp|Gender=Fem|Number=Sing",
142
- "129": "Case=Ins|Number=Plur|Person=3",
143
- "130": "Case=Loc|Number=Plur|Person=3",
144
- "131": "Case=Ins|Gender=Neut|Number=Sing|Person=3",
145
- "132": "Case=Ins|Number=Plur|Person=1",
146
- "133": "Case=Gen|Gender=Masc",
147
- "134": "Case=Ins|Gender=Fem|Number=Sing",
148
- "135": "Case=Acc",
149
- "136": "Degree=Pos|Gender=Masc|Number=Sing",
150
- "137": "Case=Dat|Number=Sing|Person=1",
151
- "138": "Case=Dat|Gender=Masc|Number=Plur|Person=3",
152
- "139": "Case=Nom|Number=Plur|Person=1",
153
- "140": "Mood=Ind|Number=Sing|Person=1|Tense=Fut|VerbForm=Fin",
154
- "141": "Case=Gen|Gender=Neut|Number=Sing|Person=3",
155
- "142": "Case=Acc|Degree=Pos|Gender=Masc|Number=Sing",
156
- "143": "Case=Ins|Degree=Pos|Number=Plur",
157
- "144": "Case=Dat|Number=Sing|Person=2",
158
- "145": "Case=Gen|Degree=Pos|Gender=Neut|Number=Sing",
159
- "146": "Case=Nom|Degree=Pos|Gender=Neut|Number=Sing",
160
- "147": "Case=Ins|Gender=Masc|Number=Plur",
161
- "148": "Case=Loc|Gender=Neut|Number=Sing",
162
- "149": "Case=Loc|Number=Sing|Person=2",
163
- "150": "Case=Loc|Number=Sing",
164
- "151": "Case=Dat|Degree=Pos|Gender=Neut|Number=Plur",
165
- "152": "Degree=Pos|Number=Plur",
166
- "153": "Case=Gen|Gender=Neut",
167
- "154": "Case=Gen|Number=Plur|Person=2",
168
- "155": "Case=Acc|Gender=Masc",
169
- "156": "Case=Dat|Gender=Masc|Number=Sing",
170
- "157": "Case=Acc|Gender=Masc|Number=Plur",
171
- "158": "Case=Ins|Number=Plur|Person=2",
172
- "159": "Case=Acc|Gender=Neut",
173
- "160": "Case=Dat",
174
- "161": "Case=Acc|Number=Sing",
175
- "162": "Case=Acc|Number=Sing|Person=1",
176
- "163": "Case=Loc|Gender=Neut",
177
- "164": "Case=Gen|Gender=Neut|Number=Sing",
178
- "165": "Case=Nom|Degree=Pos|Gender=Fem|Number=Sing",
179
- "166": "Case=Ins|Number=Sing|Person=1",
180
- "167": "Case=Loc|Degree=Cmp|Gender=Fem|Number=Sing",
181
- "168": "Case=Nom|Number=Sing|Person=1",
182
- "169": "Case=Nom|Degree=Pos|Gender=Masc|Number=Sing",
183
- "170": "Case=Dat|Gender=Fem|Number=Sing",
184
- "171": "Case=Nom|Degree=Cmp|Gender=Neut|Number=Sing",
185
- "172": "Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin",
186
- "173": "Mood=Ind|Number=Sing|Tense=Notpast|VerbForm=Fin",
187
- "174": "Case=Ins|Gender=Neut",
188
- "175": "Case=Voc|Gender=Masc|Number=Sing",
189
- "176": "Case=Gen|Number=Plur",
190
- "177": "Case=Dat|Number=Plur|Person=3",
191
- "178": "Case=Loc|Degree=Pos|Number=Plur",
192
- "179": "Degree=Pos|Gender=Neut|Number=Sing",
193
- "180": "Degree=Cmp",
194
- "181": "Case=Acc|Gender=Masc|Number=Sing",
195
- "182": "Mood=Imp|Number=Sing|Person=1|VerbForm=Fin",
196
- "183": "Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin",
197
- "184": "Case=Dat|Degree=Pos|Gender=Neut|Number=Sing",
198
- "185": "Degree=Pos",
199
- "186": "Case=Gen|Degree=Cmp|Gender=Fem|Number=Sing",
200
- "187": "Case=Loc|Number=Plur|Person=1",
201
- "188": "Mood=Ind|Number=Plur|Tense=Notpast|VerbForm=Fin",
202
- "189": "Case=Gen|Degree=Cmp|Gender=Masc|Number=Sing",
203
- "190": "Case=Acc|Number=Plur|Person=1",
204
- "191": "Case=Nom|Degree=Cmp|Gender=Fem|Number=Sing",
205
- "192": "Degree=Pos|Number=Plur|Variant=Short",
206
- "193": "Case=Nom|Gender=Masc|Number=Sing",
207
- "194": "Case=Gen|Degree=Pos|Number=Sing",
208
- "195": "Case=Loc|Gender=Masc|Number=Sing",
209
- "196": "Mood=Ind|Number=Plur|Person=3|Tense=Fut|VerbForm=Fin",
210
- "197": "Case=Ins|Number=Plur",
211
- "198": "Case=Acc|Number=Plur|Person=2",
212
- "199": "Degree=Pos|Gender=Masc|Number=Sing|Variant=Short",
213
- "200": "Case=Loc|Gender=Fem|Number=Sing|Person=3"
214
- },
215
- "initializer_range": 0.02,
216
- "intermediate_size": 3072,
217
- "label2id": {
218
- "Case=Acc": 135,
219
- "Case=Acc|Degree=Cmp|Gender=Fem|Number=Sing": 128,
220
- "Case=Acc|Degree=Cmp|Gender=Masc|Number=Sing": 39,
221
- "Case=Acc|Degree=Cmp|Gender=Neut|Number=Sing": 67,
222
- "Case=Acc|Degree=Pos|Gender=Fem|Number=Sing": 68,
223
- "Case=Acc|Degree=Pos|Gender=Masc|Number=Sing": 142,
224
- "Case=Acc|Degree=Pos|Gender=Neut|Number=Sing": 20,
225
- "Case=Acc|Degree=Pos|Number=Plur": 101,
226
- "Case=Acc|Gender=Fem|Number=Sing": 47,
227
- "Case=Acc|Gender=Fem|Number=Sing|Person=3": 114,
228
- "Case=Acc|Gender=Masc": 155,
229
- "Case=Acc|Gender=Masc|Number=Plur": 157,
230
- "Case=Acc|Gender=Masc|Number=Sing": 181,
231
- "Case=Acc|Gender=Masc|Number=Sing|Person=3": 2,
232
- "Case=Acc|Gender=Neut": 159,
233
- "Case=Acc|Gender=Neut|Number=Plur": 55,
234
- "Case=Acc|Gender=Neut|Number=Sing": 80,
235
- "Case=Acc|Gender=Neut|Number=Sing|Person=3": 98,
236
- "Case=Acc|Number=Plur": 127,
237
- "Case=Acc|Number=Plur|Person=1": 190,
238
- "Case=Acc|Number=Plur|Person=2": 198,
239
- "Case=Acc|Number=Plur|Person=3": 23,
240
- "Case=Acc|Number=Sing": 161,
241
- "Case=Acc|Number=Sing|Person=1": 162,
242
- "Case=Acc|Number=Sing|Person=2": 13,
243
- "Case=Acc|Number=Sing|Person=3": 46,
244
- "Case=Dat": 160,
245
- "Case=Dat|Degree=Cmp|Gender=Fem|Number=Sing": 52,
246
- "Case=Dat|Degree=Cmp|Gender=Neut|Number=Sing": 5,
247
- "Case=Dat|Degree=Pos|Gender=Fem|Number=Sing": 22,
248
- "Case=Dat|Degree=Pos|Gender=Masc|Number=Plur": 70,
249
- "Case=Dat|Degree=Pos|Gender=Masc|Number=Sing": 124,
250
- "Case=Dat|Degree=Pos|Gender=Neut|Number=Plur": 151,
251
- "Case=Dat|Degree=Pos|Gender=Neut|Number=Sing": 184,
252
- "Case=Dat|Degree=Pos|Number=Plur": 104,
253
- "Case=Dat|Gender=Fem|Number=Sing": 170,
254
- "Case=Dat|Gender=Fem|Number=Sing|Person=3": 120,
255
- "Case=Dat|Gender=Masc": 18,
256
- "Case=Dat|Gender=Masc|Number=Plur|Person=3": 138,
257
- "Case=Dat|Gender=Masc|Number=Sing": 156,
258
- "Case=Dat|Gender=Masc|Number=Sing|Person=3": 110,
259
- "Case=Dat|Gender=Neut": 26,
260
- "Case=Dat|Gender=Neut|Number=Sing": 111,
261
- "Case=Dat|Gender=Neut|Number=Sing|Person=3": 75,
262
- "Case=Dat|Number=Plur": 34,
263
- "Case=Dat|Number=Plur|Person=1": 49,
264
- "Case=Dat|Number=Plur|Person=2": 61,
265
- "Case=Dat|Number=Plur|Person=3": 177,
266
- "Case=Dat|Number=Sing": 78,
267
- "Case=Dat|Number=Sing|Person=1": 137,
268
- "Case=Dat|Number=Sing|Person=2": 144,
269
- "Case=Gen": 11,
270
- "Case=Gen|Degree=Cmp|Gender=Fem|Number=Sing": 186,
271
- "Case=Gen|Degree=Cmp|Gender=Masc|Number=Sing": 189,
272
- "Case=Gen|Degree=Cmp|Gender=Neut|Number=Sing": 14,
273
- "Case=Gen|Degree=Pos|Gender=Fem|Number=Sing": 122,
274
- "Case=Gen|Degree=Pos|Gender=Masc": 66,
275
- "Case=Gen|Degree=Pos|Gender=Masc|Number=Plur": 16,
276
- "Case=Gen|Degree=Pos|Gender=Masc|Number=Sing": 63,
277
- "Case=Gen|Degree=Pos|Gender=Neut|Number=Sing": 145,
278
- "Case=Gen|Degree=Pos|Number=Plur": 43,
279
- "Case=Gen|Degree=Pos|Number=Sing": 194,
280
- "Case=Gen|Gender=Fem|Number=Sing": 121,
281
- "Case=Gen|Gender=Fem|Number=Sing|Person=3": 58,
282
- "Case=Gen|Gender=Masc": 133,
283
- "Case=Gen|Gender=Masc|Number=Sing": 38,
284
- "Case=Gen|Gender=Masc|Number=Sing|Person=3": 37,
285
- "Case=Gen|Gender=Neut": 153,
286
- "Case=Gen|Gender=Neut|Number=Sing": 164,
287
- "Case=Gen|Gender=Neut|Number=Sing|Person=3": 141,
288
- "Case=Gen|Number=Plur": 176,
289
- "Case=Gen|Number=Plur|Number=Sing": 59,
290
- "Case=Gen|Number=Plur|Person=1": 24,
291
- "Case=Gen|Number=Plur|Person=2": 154,
292
- "Case=Gen|Number=Plur|Person=3": 73,
293
- "Case=Gen|Number=Sing": 102,
294
- "Case=Gen|Number=Sing|Person=1": 72,
295
- "Case=Gen|Number=Sing|Person=2": 6,
296
- "Case=Ins": 82,
297
- "Case=Ins|Degree=Cmp|Gender=Fem|Number=Sing": 62,
298
- "Case=Ins|Degree=Pos|Gender=Fem|Number=Sing": 92,
299
- "Case=Ins|Degree=Pos|Gender=Masc|Number=Sing": 125,
300
- "Case=Ins|Degree=Pos|Gender=Neut|Number=Plur": 3,
301
- "Case=Ins|Degree=Pos|Gender=Neut|Number=Sing": 93,
302
- "Case=Ins|Degree=Pos|Number=Plur": 143,
303
- "Case=Ins|Gender=Fem|Number=Sing": 134,
304
- "Case=Ins|Gender=Fem|Number=Sing|Person=3": 94,
305
- "Case=Ins|Gender=Masc": 69,
306
- "Case=Ins|Gender=Masc|Number=Plur": 147,
307
- "Case=Ins|Gender=Masc|Number=Sing": 19,
308
- "Case=Ins|Gender=Masc|Number=Sing|Person=3": 100,
309
- "Case=Ins|Gender=Neut": 174,
310
- "Case=Ins|Gender=Neut|Number=Sing": 35,
311
- "Case=Ins|Gender=Neut|Number=Sing|Person=3": 131,
312
- "Case=Ins|Number=Plur": 197,
313
- "Case=Ins|Number=Plur|Person=1": 132,
314
- "Case=Ins|Number=Plur|Person=2": 158,
315
- "Case=Ins|Number=Plur|Person=3": 129,
316
- "Case=Ins|Number=Sing": 41,
317
- "Case=Ins|Number=Sing|Person=1": 166,
318
- "Case=Ins|Number=Sing|Person=2": 10,
319
- "Case=Loc": 54,
320
- "Case=Loc|Degree=Cmp|Gender=Fem|Number=Sing": 167,
321
- "Case=Loc|Degree=Cmp|Gender=Masc|Number=Sing": 76,
322
- "Case=Loc|Degree=Cmp|Gender=Neut|Number=Sing": 95,
323
- "Case=Loc|Degree=Pos|Gender=Fem|Number=Sing": 89,
324
- "Case=Loc|Degree=Pos|Gender=Masc|Number=Sing": 8,
325
- "Case=Loc|Degree=Pos|Gender=Neut|Number=Sing": 48,
326
- "Case=Loc|Degree=Pos|Number=Plur": 178,
327
- "Case=Loc|Gender=Fem|Number=Sing": 103,
328
- "Case=Loc|Gender=Fem|Number=Sing|Person=3": 200,
329
- "Case=Loc|Gender=Masc": 60,
330
- "Case=Loc|Gender=Masc|Number=Sing": 195,
331
- "Case=Loc|Gender=Masc|Number=Sing|Person=3": 64,
332
- "Case=Loc|Gender=Neut": 163,
333
- "Case=Loc|Gender=Neut|Number=Sing": 148,
334
- "Case=Loc|Gender=Neut|Number=Sing|Person=3": 86,
335
- "Case=Loc|Number=Plur": 96,
336
- "Case=Loc|Number=Plur|Person=1": 187,
337
- "Case=Loc|Number=Plur|Person=2": 33,
338
- "Case=Loc|Number=Plur|Person=3": 130,
339
- "Case=Loc|Number=Sing": 150,
340
- "Case=Loc|Number=Sing|Person=1": 15,
341
- "Case=Loc|Number=Sing|Person=2": 149,
342
- "Case=Nom": 116,
343
- "Case=Nom|Degree=Cmp|Gender=Fem|Number=Sing": 191,
344
- "Case=Nom|Degree=Cmp|Gender=Masc|Number=Sing": 56,
345
- "Case=Nom|Degree=Cmp|Gender=Neut|Number=Sing": 171,
346
- "Case=Nom|Degree=Pos|Gender=Fem|Number=Sing": 165,
347
- "Case=Nom|Degree=Pos|Gender=Masc|Number=Sing": 169,
348
- "Case=Nom|Degree=Pos|Gender=Masc|Number=Sing|Variant=Short": 51,
349
- "Case=Nom|Degree=Pos|Gender=Neut|Number=Plur": 118,
350
- "Case=Nom|Degree=Pos|Gender=Neut|Number=Sing": 146,
351
- "Case=Nom|Degree=Pos|Number=Plur": 71,
352
- "Case=Nom|Gender=Fem|Number=Sing": 45,
353
- "Case=Nom|Gender=Fem|Number=Sing|Person=3": 77,
354
- "Case=Nom|Gender=Masc": 113,
355
- "Case=Nom|Gender=Masc|Number=Plur": 79,
356
- "Case=Nom|Gender=Masc|Number=Sing": 193,
357
- "Case=Nom|Gender=Masc|Number=Sing|Person=3": 108,
358
- "Case=Nom|Gender=Neut": 9,
359
- "Case=Nom|Gender=Neut|Number=Plur": 7,
360
- "Case=Nom|Gender=Neut|Number=Sing": 105,
361
- "Case=Nom|Gender=Neut|Number=Sing|Person=3": 119,
362
- "Case=Nom|Number=Plur": 42,
363
- "Case=Nom|Number=Plur|Number=Sing": 126,
364
- "Case=Nom|Number=Plur|Person=1": 139,
365
- "Case=Nom|Number=Plur|Person=2": 81,
366
- "Case=Nom|Number=Plur|Person=3": 84,
367
- "Case=Nom|Number=Sing": 99,
368
- "Case=Nom|Number=Sing|Person=1": 168,
369
- "Case=Nom|Number=Sing|Person=2": 31,
370
- "Case=Voc|Gender=Fem|Number=Sing": 32,
371
- "Case=Voc|Gender=Masc|Number=Sing": 175,
372
- "Degree=Cmp": 180,
373
- "Degree=Pos": 185,
374
- "Degree=Pos|Gender=Fem|Number=Sing": 57,
375
- "Degree=Pos|Gender=Fem|Number=Sing|Variant=Short": 36,
376
- "Degree=Pos|Gender=Masc|Number=Sing": 136,
377
- "Degree=Pos|Gender=Masc|Number=Sing|Variant=Short": 199,
378
- "Degree=Pos|Gender=Neut|Number=Sing": 179,
379
- "Degree=Pos|Gender=Neut|Number=Sing|Variant=Short": 107,
380
- "Degree=Pos|Number=Plur": 152,
381
- "Degree=Pos|Number=Plur|Variant=Short": 192,
382
- "Degree=Pos|Number=Sing|Variant=Short": 4,
383
- "Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin": 172,
384
- "Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin": 183,
385
- "Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin": 123,
386
- "Mood=Imp|Number=Plur|Person=1|VerbForm=Fin": 21,
387
- "Mood=Imp|Number=Plur|Person=2|VerbForm=Fin": 0,
388
- "Mood=Imp|Number=Sing|Person=1|VerbForm=Fin": 182,
389
- "Mood=Imp|Number=Sing|Person=2|VerbForm=Fin": 83,
390
- "Mood=Ind|Number=Plur|Person=1|Tense=Fut|VerbForm=Fin": 53,
391
- "Mood=Ind|Number=Plur|Person=1|Tense=Notpast|VerbForm=Fin": 28,
392
- "Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin": 29,
393
- "Mood=Ind|Number=Plur|Person=2|Tense=Fut|VerbForm=Fin": 91,
394
- "Mood=Ind|Number=Plur|Person=2|Tense=Notpast|VerbForm=Fin": 65,
395
- "Mood=Ind|Number=Plur|Person=2|Tense=Pres|VerbForm=Fin": 25,
396
- "Mood=Ind|Number=Plur|Person=3|Tense=Fut|VerbForm=Fin": 196,
397
- "Mood=Ind|Number=Plur|Person=3|Tense=Notpast|VerbForm=Fin": 27,
398
- "Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin": 50,
399
- "Mood=Ind|Number=Plur|Tense=Notpast|VerbForm=Fin": 188,
400
- "Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin": 30,
401
- "Mood=Ind|Number=Plur|Tense=Pres|VerbForm=Fin": 40,
402
- "Mood=Ind|Number=Sing|Person=1|Tense=Fut|VerbForm=Fin": 140,
403
- "Mood=Ind|Number=Sing|Person=1|Tense=Notpast|VerbForm=Fin": 112,
404
- "Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin": 74,
405
- "Mood=Ind|Number=Sing|Person=2|Tense=Fut|VerbForm=Fin": 88,
406
- "Mood=Ind|Number=Sing|Person=2|Tense=Notpast|VerbForm=Fin": 117,
407
- "Mood=Ind|Number=Sing|Person=2|Tense=Pres|VerbForm=Fin": 1,
408
- "Mood=Ind|Number=Sing|Person=3|Tense=Fut|VerbForm=Fin": 17,
409
- "Mood=Ind|Number=Sing|Person=3|Tense=Notpast|VerbForm=Fin": 85,
410
- "Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin": 44,
411
- "Mood=Ind|Number=Sing|Tense=Notpast|VerbForm=Fin": 173,
412
- "Mood=Ind|Number=Sing|Tense=Pres|VerbForm=Fin": 90,
413
- "Mood=Ind|Tense=Fut|VerbForm=Fin": 115,
414
- "Mood=Ind|Tense=Notpast|VerbForm=Fin": 87,
415
- "Mood=Ind|Tense=Pres|VerbForm=Fin": 12,
416
- "VerbForm=Conv": 106,
417
- "VerbForm=Inf": 109,
418
- "_": 97
419
- },
420
- "layer_norm_eps": 1e-12,
421
- "max_position_embeddings": 512,
422
- "model_type": "bert",
423
- "num_attention_heads": 12,
424
- "num_hidden_layers": 12,
425
- "pad_token_id": 0,
426
- "pooler_fc_size": 768,
427
- "pooler_num_attention_heads": 12,
428
- "pooler_num_fc_layers": 3,
429
- "pooler_size_per_head": 128,
430
- "pooler_type": "first_token_transform",
431
- "position_embedding_type": "absolute",
432
- "transformers_version": "4.29.2",
433
- "type_vocab_size": 2,
434
- "use_cache": true,
435
- "vocab_size": 120154
436
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_morph/syntax/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e76557974a6abb99b2515f9e8fe7adbff1a97ed1d42aa9a6cced7f15764d3eaa
3
- size 711800582
 
 
 
 
nn/nn_morph/syntax/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
nn/nn_morph/syntax/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_morph/syntax/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_morph/syntax/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/big/added_tokens.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "</w>": 120139,
3
- "<w>": 120138
4
- }
 
 
 
 
 
nn/nn_omograph/big/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_name_or_path": "ruBert-base",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "pooler_fc_size": 768,
21
- "pooler_num_attention_heads": 12,
22
- "pooler_num_fc_layers": 3,
23
- "pooler_size_per_head": 128,
24
- "pooler_type": "first_token_transform",
25
- "position_embedding_type": "absolute",
26
- "problem_type": "single_label_classification",
27
- "transformers_version": "4.29.2",
28
- "type_vocab_size": 2,
29
- "use_cache": true,
30
- "vocab_size": 120140
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/big/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b57c31f1aedf2af33169fd8d0d74501efd2be5a1bcb107125a2114f1f30bfbe4
3
- size 713508364
 
 
 
 
nn/nn_omograph/big/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
nn/nn_omograph/big/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/big/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/big/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/big_poetry/added_tokens.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "</w>": 120139,
3
- "<w>": 120138
4
- }
 
 
 
 
 
nn/nn_omograph/big_poetry/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_name_or_path": "rubert_base/",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "pooler_fc_size": 768,
21
- "pooler_num_attention_heads": 12,
22
- "pooler_num_fc_layers": 3,
23
- "pooler_size_per_head": 128,
24
- "pooler_type": "first_token_transform",
25
- "position_embedding_type": "absolute",
26
- "problem_type": "single_label_classification",
27
- "transformers_version": "4.29.2",
28
- "type_vocab_size": 2,
29
- "use_cache": true,
30
- "vocab_size": 120140
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/big_poetry/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7d1d58e5ad908f4187d3c44f640106b721e293ec954c9c4603abc25ba5f7e8a
3
- size 713508364
 
 
 
 
nn/nn_omograph/big_poetry/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
nn/nn_omograph/big_poetry/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/big_poetry/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/big_poetry/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/medium/added_tokens.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "</w>": 64001,
3
- "<w>": 64000
4
- }
 
 
 
 
 
nn/nn_omograph/medium/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_name_or_path": "ruELECTRA-medium/",
3
- "architectures": [
4
- "ElectraForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "embedding_size": 576,
9
- "generator_size": "0.25",
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 576,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 2304,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "electra",
18
- "num_attention_heads": 9,
19
- "num_hidden_layers": 12,
20
- "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
- "problem_type": "single_label_classification",
23
- "summary_activation": "gelu",
24
- "summary_last_dropout": 0.1,
25
- "summary_type": "first",
26
- "summary_use_proj": true,
27
- "transformers_version": "4.29.2",
28
- "type_vocab_size": 2,
29
- "use_cache": true,
30
- "vocab_size": 64002
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/medium/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b7f01167dae3fe025f5124d513f3d2d51cec0914ce8a7d3995b10e450d1bf38
3
- size 341725861
 
 
 
 
nn/nn_omograph/medium/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
nn/nn_omograph/medium/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/medium/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "ElectraTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/medium/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/medium_poetry/added_tokens.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "</w>": 64001,
3
- "<w>": 64000
4
- }
 
 
 
 
 
nn/nn_omograph/medium_poetry/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_name_or_path": "SRUElectra-medium/checkpoint-4500000/",
3
- "architectures": [
4
- "ElectraForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "embedding_size": 576,
9
- "generator_size": "0.25",
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 576,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 2304,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "electra",
18
- "num_attention_heads": 9,
19
- "num_hidden_layers": 12,
20
- "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
- "problem_type": "single_label_classification",
23
- "summary_activation": "gelu",
24
- "summary_last_dropout": 0.1,
25
- "summary_type": "first",
26
- "summary_use_proj": true,
27
- "transformers_version": "4.29.2",
28
- "type_vocab_size": 2,
29
- "use_cache": true,
30
- "vocab_size": 64002
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/medium_poetry/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:689752e4bff9eb0b8837482d9ea724f72356aab19822c2e4ae3de6b5a2fc08b1
3
- size 341725861
 
 
 
 
nn/nn_omograph/medium_poetry/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
nn/nn_omograph/medium_poetry/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/medium_poetry/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "ElectraTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
nn/nn_omograph/medium_poetry/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
nn/nn_omograph/small/added_tokens.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "</w>": 83829,
3
- "<w>": 83828
4
- }
 
 
 
 
 
nn/nn_omograph/small/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "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
- "initializer_range": 0.02,
14
- "intermediate_size": 600,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 2048,
17
- "model_type": "bert",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 3,
20
- "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
- "problem_type": "single_label_classification",
23
- "transformers_version": "4.29.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 83830
27
- }