martincc98
commited on
Commit
•
a4e7324
1
Parent(s):
a4fd127
Upload tokenizer
Browse files- special_tokens_map.json +5 -35
- tokenizer_config.json +0 -7
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
}
|
|
|
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
@@ -46,18 +46,11 @@
|
|
46 |
"do_basic_tokenize": false,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"max_length": 64,
|
50 |
"model_max_length": 512,
|
51 |
-
"pad_to_multiple_of": null,
|
52 |
"pad_token": "[PAD]",
|
53 |
-
"pad_token_type_id": 0,
|
54 |
-
"padding_side": "right",
|
55 |
"sep_token": "[SEP]",
|
56 |
-
"stride": 0,
|
57 |
"strip_accents": null,
|
58 |
"tokenize_chinese_chars": true,
|
59 |
"tokenizer_class": "DistilBertTokenizer",
|
60 |
-
"truncation_side": "right",
|
61 |
-
"truncation_strategy": "longest_first",
|
62 |
"unk_token": "[UNK]"
|
63 |
}
|
|
|
46 |
"do_basic_tokenize": false,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
|
|
49 |
"model_max_length": 512,
|
|
|
50 |
"pad_token": "[PAD]",
|
|
|
|
|
51 |
"sep_token": "[SEP]",
|
|
|
52 |
"strip_accents": null,
|
53 |
"tokenize_chinese_chars": true,
|
54 |
"tokenizer_class": "DistilBertTokenizer",
|
|
|
|
|
55 |
"unk_token": "[UNK]"
|
56 |
}
|