Commit
•
ed79aa7
1
Parent(s):
a93d04a
Upload tokenizer
Browse files- tokenizer.json +22 -22
- tokenizer_config.json +22 -22
tokenizer.json
CHANGED
@@ -7,8 +7,8 @@
|
|
7 |
"id": 0,
|
8 |
"content": ">>TITLE<<",
|
9 |
"single_word": false,
|
10 |
-
"lstrip":
|
11 |
-
"rstrip":
|
12 |
"normalized": false,
|
13 |
"special": true
|
14 |
},
|
@@ -16,8 +16,8 @@
|
|
16 |
"id": 1,
|
17 |
"content": ">>ABSTRACT<<",
|
18 |
"single_word": false,
|
19 |
-
"lstrip":
|
20 |
-
"rstrip":
|
21 |
"normalized": false,
|
22 |
"special": true
|
23 |
},
|
@@ -25,8 +25,8 @@
|
|
25 |
"id": 2,
|
26 |
"content": ">>INTRODUCTION<<",
|
27 |
"single_word": false,
|
28 |
-
"lstrip":
|
29 |
-
"rstrip":
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
},
|
@@ -34,8 +34,8 @@
|
|
34 |
"id": 3,
|
35 |
"content": ">>SUMMARY<<",
|
36 |
"single_word": false,
|
37 |
-
"lstrip":
|
38 |
-
"rstrip":
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
},
|
@@ -43,8 +43,8 @@
|
|
43 |
"id": 4,
|
44 |
"content": ">>COMMENT<<",
|
45 |
"single_word": false,
|
46 |
-
"lstrip":
|
47 |
-
"rstrip":
|
48 |
"normalized": false,
|
49 |
"special": true
|
50 |
},
|
@@ -52,8 +52,8 @@
|
|
52 |
"id": 5,
|
53 |
"content": ">>ANSWER<<",
|
54 |
"single_word": false,
|
55 |
-
"lstrip":
|
56 |
-
"rstrip":
|
57 |
"normalized": false,
|
58 |
"special": true
|
59 |
},
|
@@ -61,8 +61,8 @@
|
|
61 |
"id": 6,
|
62 |
"content": ">>QUESTION<<",
|
63 |
"single_word": false,
|
64 |
-
"lstrip":
|
65 |
-
"rstrip":
|
66 |
"normalized": false,
|
67 |
"special": true
|
68 |
},
|
@@ -70,8 +70,8 @@
|
|
70 |
"id": 7,
|
71 |
"content": ">>DOMAIN<<",
|
72 |
"single_word": false,
|
73 |
-
"lstrip":
|
74 |
-
"rstrip":
|
75 |
"normalized": false,
|
76 |
"special": true
|
77 |
},
|
@@ -79,8 +79,8 @@
|
|
79 |
"id": 8,
|
80 |
"content": ">>PREFIX<<",
|
81 |
"single_word": false,
|
82 |
-
"lstrip":
|
83 |
-
"rstrip":
|
84 |
"normalized": false,
|
85 |
"special": true
|
86 |
},
|
@@ -88,8 +88,8 @@
|
|
88 |
"id": 9,
|
89 |
"content": ">>SUFFIX<<",
|
90 |
"single_word": false,
|
91 |
-
"lstrip":
|
92 |
-
"rstrip":
|
93 |
"normalized": false,
|
94 |
"special": true
|
95 |
},
|
@@ -97,8 +97,8 @@
|
|
97 |
"id": 10,
|
98 |
"content": ">>MIDDLE<<",
|
99 |
"single_word": false,
|
100 |
-
"lstrip":
|
101 |
-
"rstrip":
|
102 |
"normalized": false,
|
103 |
"special": true
|
104 |
},
|
|
|
7 |
"id": 0,
|
8 |
"content": ">>TITLE<<",
|
9 |
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
"normalized": false,
|
13 |
"special": true
|
14 |
},
|
|
|
16 |
"id": 1,
|
17 |
"content": ">>ABSTRACT<<",
|
18 |
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
"normalized": false,
|
22 |
"special": true
|
23 |
},
|
|
|
25 |
"id": 2,
|
26 |
"content": ">>INTRODUCTION<<",
|
27 |
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
},
|
|
|
34 |
"id": 3,
|
35 |
"content": ">>SUMMARY<<",
|
36 |
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
},
|
|
|
43 |
"id": 4,
|
44 |
"content": ">>COMMENT<<",
|
45 |
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
50 |
},
|
|
|
52 |
"id": 5,
|
53 |
"content": ">>ANSWER<<",
|
54 |
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
"normalized": false,
|
58 |
"special": true
|
59 |
},
|
|
|
61 |
"id": 6,
|
62 |
"content": ">>QUESTION<<",
|
63 |
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
"normalized": false,
|
67 |
"special": true
|
68 |
},
|
|
|
70 |
"id": 7,
|
71 |
"content": ">>DOMAIN<<",
|
72 |
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": false,
|
75 |
"normalized": false,
|
76 |
"special": true
|
77 |
},
|
|
|
79 |
"id": 8,
|
80 |
"content": ">>PREFIX<<",
|
81 |
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": false,
|
84 |
"normalized": false,
|
85 |
"special": true
|
86 |
},
|
|
|
88 |
"id": 9,
|
89 |
"content": ">>SUFFIX<<",
|
90 |
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": false,
|
93 |
"normalized": false,
|
94 |
"special": true
|
95 |
},
|
|
|
97 |
"id": 10,
|
98 |
"content": ">>MIDDLE<<",
|
99 |
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": false,
|
102 |
"normalized": false,
|
103 |
"special": true
|
104 |
},
|
tokenizer_config.json
CHANGED
@@ -3,89 +3,89 @@
|
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": ">>TITLE<<",
|
6 |
-
"lstrip":
|
7 |
"normalized": false,
|
8 |
-
"rstrip":
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
"content": ">>ABSTRACT<<",
|
14 |
-
"lstrip":
|
15 |
"normalized": false,
|
16 |
-
"rstrip":
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
"content": ">>INTRODUCTION<<",
|
22 |
-
"lstrip":
|
23 |
"normalized": false,
|
24 |
-
"rstrip":
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
"3": {
|
29 |
"content": ">>SUMMARY<<",
|
30 |
-
"lstrip":
|
31 |
"normalized": false,
|
32 |
-
"rstrip":
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
"4": {
|
37 |
"content": ">>COMMENT<<",
|
38 |
-
"lstrip":
|
39 |
"normalized": false,
|
40 |
-
"rstrip":
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
},
|
44 |
"5": {
|
45 |
"content": ">>ANSWER<<",
|
46 |
-
"lstrip":
|
47 |
"normalized": false,
|
48 |
-
"rstrip":
|
49 |
"single_word": false,
|
50 |
"special": true
|
51 |
},
|
52 |
"6": {
|
53 |
"content": ">>QUESTION<<",
|
54 |
-
"lstrip":
|
55 |
"normalized": false,
|
56 |
-
"rstrip":
|
57 |
"single_word": false,
|
58 |
"special": true
|
59 |
},
|
60 |
"7": {
|
61 |
"content": ">>DOMAIN<<",
|
62 |
-
"lstrip":
|
63 |
"normalized": false,
|
64 |
-
"rstrip":
|
65 |
"single_word": false,
|
66 |
"special": true
|
67 |
},
|
68 |
"8": {
|
69 |
"content": ">>PREFIX<<",
|
70 |
-
"lstrip":
|
71 |
"normalized": false,
|
72 |
-
"rstrip":
|
73 |
"single_word": false,
|
74 |
"special": true
|
75 |
},
|
76 |
"9": {
|
77 |
"content": ">>SUFFIX<<",
|
78 |
-
"lstrip":
|
79 |
"normalized": false,
|
80 |
-
"rstrip":
|
81 |
"single_word": false,
|
82 |
"special": true
|
83 |
},
|
84 |
"10": {
|
85 |
"content": ">>MIDDLE<<",
|
86 |
-
"lstrip":
|
87 |
"normalized": false,
|
88 |
-
"rstrip":
|
89 |
"single_word": false,
|
90 |
"special": true
|
91 |
},
|
|
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": ">>TITLE<<",
|
6 |
+
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
"content": ">>ABSTRACT<<",
|
14 |
+
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
"content": ">>INTRODUCTION<<",
|
22 |
+
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
"3": {
|
29 |
"content": ">>SUMMARY<<",
|
30 |
+
"lstrip": false,
|
31 |
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
"4": {
|
37 |
"content": ">>COMMENT<<",
|
38 |
+
"lstrip": false,
|
39 |
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
},
|
44 |
"5": {
|
45 |
"content": ">>ANSWER<<",
|
46 |
+
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
"single_word": false,
|
50 |
"special": true
|
51 |
},
|
52 |
"6": {
|
53 |
"content": ">>QUESTION<<",
|
54 |
+
"lstrip": false,
|
55 |
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
"single_word": false,
|
58 |
"special": true
|
59 |
},
|
60 |
"7": {
|
61 |
"content": ">>DOMAIN<<",
|
62 |
+
"lstrip": false,
|
63 |
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
"single_word": false,
|
66 |
"special": true
|
67 |
},
|
68 |
"8": {
|
69 |
"content": ">>PREFIX<<",
|
70 |
+
"lstrip": false,
|
71 |
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
"single_word": false,
|
74 |
"special": true
|
75 |
},
|
76 |
"9": {
|
77 |
"content": ">>SUFFIX<<",
|
78 |
+
"lstrip": false,
|
79 |
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
"single_word": false,
|
82 |
"special": true
|
83 |
},
|
84 |
"10": {
|
85 |
"content": ">>MIDDLE<<",
|
86 |
+
"lstrip": false,
|
87 |
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
"single_word": false,
|
90 |
"special": true
|
91 |
},
|