Upload tokenizer
Browse files- special_tokens_map.json +21 -3
- tokenizer_config.json +74 -74
special_tokens_map.json
CHANGED
@@ -1,5 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -16,40 +16,72 @@
|
|
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 |
-
"
|
44 |
-
"content": "<
|
45 |
"lstrip": false,
|
46 |
"normalized": false,
|
47 |
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": true
|
50 |
},
|
51 |
-
"
|
52 |
-
"content": "<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
"lstrip": false,
|
54 |
"normalized": false,
|
55 |
"rstrip": false,
|
@@ -128,14 +160,6 @@
|
|
128 |
"single_word": false,
|
129 |
"special": true
|
130 |
},
|
131 |
-
"2": {
|
132 |
-
"content": "</s>",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": true
|
138 |
-
},
|
139 |
"20": {
|
140 |
"content": "<extra_id_16>",
|
141 |
"lstrip": false,
|
@@ -216,14 +240,6 @@
|
|
216 |
"single_word": false,
|
217 |
"special": true
|
218 |
},
|
219 |
-
"3": {
|
220 |
-
"content": "<pad>",
|
221 |
-
"lstrip": false,
|
222 |
-
"normalized": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"single_word": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
"30": {
|
228 |
"content": "<extra_id_26>",
|
229 |
"lstrip": false,
|
@@ -304,14 +320,6 @@
|
|
304 |
"single_word": false,
|
305 |
"special": true
|
306 |
},
|
307 |
-
"4": {
|
308 |
-
"content": "<extra_id_0>",
|
309 |
-
"lstrip": false,
|
310 |
-
"normalized": false,
|
311 |
-
"rstrip": false,
|
312 |
-
"single_word": false,
|
313 |
-
"special": true
|
314 |
-
},
|
315 |
"40": {
|
316 |
"content": "<extra_id_36>",
|
317 |
"lstrip": false,
|
@@ -392,14 +400,6 @@
|
|
392 |
"single_word": false,
|
393 |
"special": true
|
394 |
},
|
395 |
-
"5": {
|
396 |
-
"content": "<extra_id_1>",
|
397 |
-
"lstrip": false,
|
398 |
-
"normalized": false,
|
399 |
-
"rstrip": false,
|
400 |
-
"single_word": false,
|
401 |
-
"special": true
|
402 |
-
},
|
403 |
"50": {
|
404 |
"content": "<extra_id_46>",
|
405 |
"lstrip": false,
|
@@ -480,14 +480,6 @@
|
|
480 |
"single_word": false,
|
481 |
"special": true
|
482 |
},
|
483 |
-
"6": {
|
484 |
-
"content": "<extra_id_2>",
|
485 |
-
"lstrip": false,
|
486 |
-
"normalized": false,
|
487 |
-
"rstrip": false,
|
488 |
-
"single_word": false,
|
489 |
-
"special": true
|
490 |
-
},
|
491 |
"60": {
|
492 |
"content": "<extra_id_56>",
|
493 |
"lstrip": false,
|
@@ -568,14 +560,6 @@
|
|
568 |
"single_word": false,
|
569 |
"special": true
|
570 |
},
|
571 |
-
"7": {
|
572 |
-
"content": "<extra_id_3>",
|
573 |
-
"lstrip": false,
|
574 |
-
"normalized": false,
|
575 |
-
"rstrip": false,
|
576 |
-
"single_word": false,
|
577 |
-
"special": true
|
578 |
-
},
|
579 |
"70": {
|
580 |
"content": "<extra_id_66>",
|
581 |
"lstrip": false,
|
@@ -656,14 +640,6 @@
|
|
656 |
"single_word": false,
|
657 |
"special": true
|
658 |
},
|
659 |
-
"8": {
|
660 |
-
"content": "<extra_id_4>",
|
661 |
-
"lstrip": false,
|
662 |
-
"normalized": false,
|
663 |
-
"rstrip": false,
|
664 |
-
"single_word": false,
|
665 |
-
"special": true
|
666 |
-
},
|
667 |
"80": {
|
668 |
"content": "<extra_id_76>",
|
669 |
"lstrip": false,
|
@@ -744,14 +720,6 @@
|
|
744 |
"single_word": false,
|
745 |
"special": true
|
746 |
},
|
747 |
-
"9": {
|
748 |
-
"content": "<extra_id_5>",
|
749 |
-
"lstrip": false,
|
750 |
-
"normalized": false,
|
751 |
-
"rstrip": false,
|
752 |
-
"single_word": false,
|
753 |
-
"special": true
|
754 |
-
},
|
755 |
"90": {
|
756 |
"content": "<extra_id_86>",
|
757 |
"lstrip": false,
|
@@ -831,6 +799,38 @@
|
|
831 |
"rstrip": false,
|
832 |
"single_word": false,
|
833 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
834 |
}
|
835 |
},
|
836 |
"additional_special_tokens": [],
|
|
|
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": "<pad>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"4": {
|
36 |
+
"content": "<extra_id_0>",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
},
|
43 |
+
"5": {
|
44 |
+
"content": "<extra_id_1>",
|
45 |
"lstrip": false,
|
46 |
"normalized": false,
|
47 |
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": true
|
50 |
},
|
51 |
+
"6": {
|
52 |
+
"content": "<extra_id_2>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<extra_id_3>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<extra_id_4>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "<extra_id_5>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "<extra_id_6>",
|
85 |
"lstrip": false,
|
86 |
"normalized": false,
|
87 |
"rstrip": false,
|
|
|
160 |
"single_word": false,
|
161 |
"special": true
|
162 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
"20": {
|
164 |
"content": "<extra_id_16>",
|
165 |
"lstrip": false,
|
|
|
240 |
"single_word": false,
|
241 |
"special": true
|
242 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
243 |
"30": {
|
244 |
"content": "<extra_id_26>",
|
245 |
"lstrip": false,
|
|
|
320 |
"single_word": false,
|
321 |
"special": true
|
322 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
323 |
"40": {
|
324 |
"content": "<extra_id_36>",
|
325 |
"lstrip": false,
|
|
|
400 |
"single_word": false,
|
401 |
"special": true
|
402 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
403 |
"50": {
|
404 |
"content": "<extra_id_46>",
|
405 |
"lstrip": false,
|
|
|
480 |
"single_word": false,
|
481 |
"special": true
|
482 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
483 |
"60": {
|
484 |
"content": "<extra_id_56>",
|
485 |
"lstrip": false,
|
|
|
560 |
"single_word": false,
|
561 |
"special": true
|
562 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
563 |
"70": {
|
564 |
"content": "<extra_id_66>",
|
565 |
"lstrip": false,
|
|
|
640 |
"single_word": false,
|
641 |
"special": true
|
642 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
643 |
"80": {
|
644 |
"content": "<extra_id_76>",
|
645 |
"lstrip": false,
|
|
|
720 |
"single_word": false,
|
721 |
"special": true
|
722 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
723 |
"90": {
|
724 |
"content": "<extra_id_86>",
|
725 |
"lstrip": false,
|
|
|
799 |
"rstrip": false,
|
800 |
"single_word": false,
|
801 |
"special": true
|
802 |
+
},
|
803 |
+
"100": {
|
804 |
+
"content": "<extra_id_96>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"101": {
|
812 |
+
"content": "<extra_id_97>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"102": {
|
820 |
+
"content": "<extra_id_98>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"103": {
|
828 |
+
"content": "<extra_id_99>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
}
|
835 |
},
|
836 |
"additional_special_tokens": [],
|