Hugging Face's logo

buddhist-nlp
/
mitra-mnt-zh-en

Translation
Transformers
PyTorch
Chinese
English
m2m_100
text2text-generation
Inference Endpoints
Model card Files Community
snehrdich commited on
Commit
fe1cd1f
•
1 Parent(s): 5091146

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +10 -0
  2. sentencepiece.bpe.model +3 -0
  3. special_tokens_map.json +17 -0
  4. tokenizer_config.json +123 -0
  5. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__cs__": 128005,
3
+ "__de__": 128008,
4
+ "__en__": 128001,
5
+ "__ha__": 128002,
6
+ "__is__": 128003,
7
+ "__ja__": 128004,
8
+ "__ru__": 128006,
9
+ "__zh__": 128007
10
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cad99b5428aa4802c265015a12dd8a18a43b9d53a3ae8cc123e7e25aba7ef4f
3
+ size 2586236
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__en__",
4
+ "__ha__",
5
+ "__is__",
6
+ "__ja__",
7
+ "__cs__",
8
+ "__ru__",
9
+ "__zh__",
10
+ "__de__"
11
+ ],
12
+ "bos_token": "<s>",
13
+ "eos_token": "</s>",
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "unk_token": "<unk>"
17
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128001": {
36
+ "content": "__en__",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128002": {
44
+ "content": "__ha__",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128003": {
52
+ "content": "__is__",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128004": {
60
+ "content": "__ja__",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128005": {
68
+ "content": "__cs__",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128006": {
76
+ "content": "__ru__",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128007": {
84
+ "content": "__zh__",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128008": {
92
+ "content": "__de__",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ }
99
+ },
100
+ "additional_special_tokens": [
101
+ "__en__",
102
+ "__ha__",
103
+ "__is__",
104
+ "__ja__",
105
+ "__cs__",
106
+ "__ru__",
107
+ "__zh__",
108
+ "__de__"
109
+ ],
110
+ "bos_token": "<s>",
111
+ "clean_up_tokenization_spaces": true,
112
+ "eos_token": "</s>",
113
+ "language_codes": "wmt21",
114
+ "model_max_length": 1000000000000000019884624838656,
115
+ "num_madeup_words": 0,
116
+ "pad_token": "<pad>",
117
+ "sep_token": "</s>",
118
+ "sp_model_kwargs": {},
119
+ "src_lang": "en",
120
+ "tgt_lang": "en",
121
+ "tokenizer_class": "M2M100Tokenizer",
122
+ "unk_token": "<unk>"
123
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff