Upload tokenizer
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +63 -0
- tokenizer.json +0 -0
- tokenizer_config.json +110 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 65537,
|
3 |
+
"<mask>": 65540,
|
4 |
+
"<pad>": 65539,
|
5 |
+
"<s>": 65536,
|
6 |
+
"<unk>": 65538
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[UNK]",
|
4 |
+
"[PAD]",
|
5 |
+
"[CLS]",
|
6 |
+
"[SEP]",
|
7 |
+
"[MASK]",
|
8 |
+
"<s>",
|
9 |
+
"</s>",
|
10 |
+
"<unk>",
|
11 |
+
"<pad>",
|
12 |
+
"<mask>"
|
13 |
+
],
|
14 |
+
"bos_token": {
|
15 |
+
"content": "[CLS]",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"cls_token": {
|
22 |
+
"content": "[CLS]",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"eos_token": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"mask_token": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
},
|
42 |
+
"pad_token": {
|
43 |
+
"content": "[PAD]",
|
44 |
+
"lstrip": false,
|
45 |
+
"normalized": false,
|
46 |
+
"rstrip": false,
|
47 |
+
"single_word": false
|
48 |
+
},
|
49 |
+
"sep_token": {
|
50 |
+
"content": "[SEP]",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": false,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
},
|
56 |
+
"unk_token": {
|
57 |
+
"content": "[UNK]",
|
58 |
+
"lstrip": false,
|
59 |
+
"normalized": false,
|
60 |
+
"rstrip": false,
|
61 |
+
"single_word": false
|
62 |
+
}
|
63 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[UNK]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "[PAD]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "[CLS]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "[MASK]",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"65536": {
|
45 |
+
"content": "<s>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"65537": {
|
53 |
+
"content": "</s>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"65538": {
|
61 |
+
"content": "<unk>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"65539": {
|
69 |
+
"content": "<pad>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"65540": {
|
77 |
+
"content": "<mask>",
|
78 |
+
"lstrip": true,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"additional_special_tokens": [
|
86 |
+
"[UNK]",
|
87 |
+
"[PAD]",
|
88 |
+
"[CLS]",
|
89 |
+
"[SEP]",
|
90 |
+
"[MASK]",
|
91 |
+
"<s>",
|
92 |
+
"</s>",
|
93 |
+
"<unk>",
|
94 |
+
"<pad>",
|
95 |
+
"<mask>"
|
96 |
+
],
|
97 |
+
"bos_token": "[CLS]",
|
98 |
+
"clean_up_tokenization_spaces": true,
|
99 |
+
"cls_token": "[CLS]",
|
100 |
+
"eos_token": "[SEP]",
|
101 |
+
"errors": "replace",
|
102 |
+
"mask_token": "[MASK]",
|
103 |
+
"max_len": 512,
|
104 |
+
"model_max_length": 512,
|
105 |
+
"pad_token": "[PAD]",
|
106 |
+
"sep_token": "[SEP]",
|
107 |
+
"tokenizer_class": "RobertaTokenizer",
|
108 |
+
"trim_offsets": true,
|
109 |
+
"unk_token": "[UNK]"
|
110 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|