Commit
•
1d4443a
1
Parent(s):
6726507
Upload tokenizer
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +5 -49
- tokenizer_config.json +21 -34
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 24311,
|
3 |
+
"[MASK]": 24312,
|
4 |
+
"[PAD]": 24310,
|
5 |
+
"[SEP]": 24309,
|
6 |
+
"[UNK]": 24308
|
7 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,51 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "<cls>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "<e>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "<mask>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "<pad>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "<sep>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
-
"unk_token": {
|
45 |
-
"content": "$",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false
|
50 |
-
}
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,39 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"22117": {
|
44 |
-
"content": "<cls>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"22118": {
|
52 |
-
"content": "<mask>",
|
53 |
"lstrip": false,
|
54 |
"normalized": false,
|
55 |
"rstrip": false,
|
@@ -57,14 +41,17 @@
|
|
57 |
"special": true
|
58 |
}
|
59 |
},
|
60 |
-
"bos_token": "<s>",
|
61 |
"clean_up_tokenization_spaces": true,
|
62 |
-
"cls_token": "
|
63 |
-
"
|
64 |
-
"
|
|
|
65 |
"model_max_length": 1000000000000000019884624838656,
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
|
|
|
|
|
|
70 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"24308": {
|
4 |
+
"content": "[UNK]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"24309": {
|
12 |
+
"content": "[SEP]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"24310": {
|
20 |
+
"content": "[PAD]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"24311": {
|
28 |
+
"content": "[CLS]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"24312": {
|
36 |
+
"content": "[MASK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|