anzorq commited on
Commit
f91e37f
1 Parent(s): 80274ad

add tokenizer

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
special_tokens_map.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "</s>",
108
+ "unk_token": "<unk>"
109
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "language_codes": "m2m100",
107
+ "model_max_length": 1024,
108
+ "name_or_path": "facebook/m2m100_418M",
109
+ "num_madeup_words": 8,
110
+ "pad_token": "<pad>",
111
+ "sep_token": "</s>",
112
+ "sp_model_kwargs": {},
113
+ "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json",
114
+ "src_lang": "ru",
115
+ "tgt_lang": "zu",
116
+ "tokenizer_class": "M2M100Tokenizer",
117
+ "tokenizer_file": null,
118
+ "unk_token": "<unk>"
119
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff