yeshpanovrustem commited on
Commit
de245bc
1 Parent(s): 4e86c63

Upload 4 files

Browse files
.gitattributes ADDED
@@ -0,0 +1 @@
 
 
1
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40",
55
+ "41": "LABEL_41",
56
+ "42": "LABEL_42",
57
+ "43": "LABEL_43",
58
+ "44": "LABEL_44",
59
+ "45": "LABEL_45",
60
+ "46": "LABEL_46",
61
+ "47": "LABEL_47",
62
+ "48": "LABEL_48",
63
+ "49": "LABEL_49",
64
+ "50": "LABEL_50"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1,
71
+ "LABEL_10": 10,
72
+ "LABEL_11": 11,
73
+ "LABEL_12": 12,
74
+ "LABEL_13": 13,
75
+ "LABEL_14": 14,
76
+ "LABEL_15": 15,
77
+ "LABEL_16": 16,
78
+ "LABEL_17": 17,
79
+ "LABEL_18": 18,
80
+ "LABEL_19": 19,
81
+ "LABEL_2": 2,
82
+ "LABEL_20": 20,
83
+ "LABEL_21": 21,
84
+ "LABEL_22": 22,
85
+ "LABEL_23": 23,
86
+ "LABEL_24": 24,
87
+ "LABEL_25": 25,
88
+ "LABEL_26": 26,
89
+ "LABEL_27": 27,
90
+ "LABEL_28": 28,
91
+ "LABEL_29": 29,
92
+ "LABEL_3": 3,
93
+ "LABEL_30": 30,
94
+ "LABEL_31": 31,
95
+ "LABEL_32": 32,
96
+ "LABEL_33": 33,
97
+ "LABEL_34": 34,
98
+ "LABEL_35": 35,
99
+ "LABEL_36": 36,
100
+ "LABEL_37": 37,
101
+ "LABEL_38": 38,
102
+ "LABEL_39": 39,
103
+ "LABEL_4": 4,
104
+ "LABEL_40": 40,
105
+ "LABEL_41": 41,
106
+ "LABEL_42": 42,
107
+ "LABEL_43": 43,
108
+ "LABEL_44": 44,
109
+ "LABEL_45": 45,
110
+ "LABEL_46": 46,
111
+ "LABEL_47": 47,
112
+ "LABEL_48": 48,
113
+ "LABEL_49": 49,
114
+ "LABEL_5": 5,
115
+ "LABEL_50": 50,
116
+ "LABEL_6": 6,
117
+ "LABEL_7": 7,
118
+ "LABEL_8": 8,
119
+ "LABEL_9": 9
120
+ },
121
+ "layer_norm_eps": 1e-05,
122
+ "max_position_embeddings": 514,
123
+ "model_type": "xlm-roberta",
124
+ "num_attention_heads": 16,
125
+ "num_hidden_layers": 24,
126
+ "output_past": true,
127
+ "pad_token_id": 1,
128
+ "position_embedding_type": "absolute",
129
+ "torch_dtype": "float32",
130
+ "transformers_version": "4.29.2",
131
+ "type_vocab_size": 1,
132
+ "use_cache": true,
133
+ "vocab_size": 250002
134
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }