Upload processor
Browse files- added_tokens.json +1 -6
- special_tokens_map.json +7 -1
- tokenizer_config.json +8 -9
added_tokens.json
CHANGED
@@ -1,8 +1,3 @@
|
|
1 |
{
|
2 |
-
"[
|
3 |
-
"[DEC]": 30522,
|
4 |
-
"[MASK]": 103,
|
5 |
-
"[PAD]": 0,
|
6 |
-
"[SEP]": 102,
|
7 |
-
"[UNK]": 100
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"[DEC]": 30522
|
|
|
|
|
|
|
|
|
|
|
3 |
}
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,11 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"cls_token": "[CLS]",
|
4 |
"mask_token": "[MASK]",
|
5 |
"pad_token": "[PAD]",
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[DEC]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"cls_token": "[CLS]",
|
10 |
"mask_token": "[MASK]",
|
11 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
@@ -6,7 +6,7 @@
|
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
-
"special":
|
10 |
},
|
11 |
"100": {
|
12 |
"content": "[UNK]",
|
@@ -14,7 +14,7 @@
|
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
-
"special":
|
18 |
},
|
19 |
"101": {
|
20 |
"content": "[CLS]",
|
@@ -22,7 +22,7 @@
|
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
-
"special":
|
26 |
},
|
27 |
"102": {
|
28 |
"content": "[SEP]",
|
@@ -30,7 +30,7 @@
|
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
-
"special":
|
34 |
},
|
35 |
"103": {
|
36 |
"content": "[MASK]",
|
@@ -38,18 +38,18 @@
|
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
-
"special":
|
42 |
},
|
43 |
"30522": {
|
44 |
"content": "[DEC]",
|
45 |
-
"lstrip":
|
46 |
"normalized": false,
|
47 |
-
"rstrip":
|
48 |
"single_word": false,
|
49 |
"special": true
|
50 |
}
|
51 |
},
|
52 |
-
"
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
"cls_token": "[CLS]",
|
55 |
"do_basic_tokenize": true,
|
@@ -63,7 +63,6 @@
|
|
63 |
"strip_accents": null,
|
64 |
"tokenize_chinese_chars": true,
|
65 |
"tokenizer_class": "BertTokenizer",
|
66 |
-
"tokenizer_file": null,
|
67 |
"truncation_side": "right",
|
68 |
"unk_token": "[UNK]"
|
69 |
}
|
|
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
+
"special": true
|
10 |
},
|
11 |
"100": {
|
12 |
"content": "[UNK]",
|
|
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
+
"special": true
|
18 |
},
|
19 |
"101": {
|
20 |
"content": "[CLS]",
|
|
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
+
"special": true
|
26 |
},
|
27 |
"102": {
|
28 |
"content": "[SEP]",
|
|
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
+
"special": true
|
34 |
},
|
35 |
"103": {
|
36 |
"content": "[MASK]",
|
|
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
+
"special": true
|
42 |
},
|
43 |
"30522": {
|
44 |
"content": "[DEC]",
|
45 |
+
"lstrip": false,
|
46 |
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": true
|
50 |
}
|
51 |
},
|
52 |
+
"bos_token": "[DEC]",
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
"cls_token": "[CLS]",
|
55 |
"do_basic_tokenize": true,
|
|
|
63 |
"strip_accents": null,
|
64 |
"tokenize_chinese_chars": true,
|
65 |
"tokenizer_class": "BertTokenizer",
|
|
|
66 |
"truncation_side": "right",
|
67 |
"unk_token": "[UNK]"
|
68 |
}
|