johngiorgi
commited on
Commit
•
e4098c3
1
Parent(s):
780539e
Upload tokenizer.json
Browse files- tokenizer.json +0 -117
tokenizer.json
CHANGED
@@ -47,123 +47,6 @@
|
|
47 |
"rstrip": false,
|
48 |
"normalized": true,
|
49 |
"special": true
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"id": 50265,
|
53 |
-
"content": "<background>",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"id": 50266,
|
62 |
-
"content": "</background>",
|
63 |
-
"single_word": false,
|
64 |
-
"lstrip": false,
|
65 |
-
"rstrip": false,
|
66 |
-
"normalized": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
{
|
70 |
-
"id": 50267,
|
71 |
-
"content": "<ref>",
|
72 |
-
"single_word": false,
|
73 |
-
"lstrip": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"normalized": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
{
|
79 |
-
"id": 50268,
|
80 |
-
"content": "</ref>",
|
81 |
-
"single_word": false,
|
82 |
-
"lstrip": false,
|
83 |
-
"rstrip": false,
|
84 |
-
"normalized": false,
|
85 |
-
"special": true
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"id": 50269,
|
89 |
-
"content": "<sep>",
|
90 |
-
"single_word": false,
|
91 |
-
"lstrip": false,
|
92 |
-
"rstrip": false,
|
93 |
-
"normalized": false,
|
94 |
-
"special": true
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"id": 50270,
|
98 |
-
"content": "<pop>",
|
99 |
-
"single_word": false,
|
100 |
-
"lstrip": false,
|
101 |
-
"rstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"special": true
|
104 |
-
},
|
105 |
-
{
|
106 |
-
"id": 50271,
|
107 |
-
"content": "</pop>",
|
108 |
-
"single_word": false,
|
109 |
-
"lstrip": false,
|
110 |
-
"rstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"special": true
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"id": 50272,
|
116 |
-
"content": "<int>",
|
117 |
-
"single_word": false,
|
118 |
-
"lstrip": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"normalized": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"id": 50273,
|
125 |
-
"content": "</int>",
|
126 |
-
"single_word": false,
|
127 |
-
"lstrip": false,
|
128 |
-
"rstrip": false,
|
129 |
-
"normalized": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"id": 50274,
|
134 |
-
"content": "<out>",
|
135 |
-
"single_word": false,
|
136 |
-
"lstrip": false,
|
137 |
-
"rstrip": false,
|
138 |
-
"normalized": false,
|
139 |
-
"special": true
|
140 |
-
},
|
141 |
-
{
|
142 |
-
"id": 50275,
|
143 |
-
"content": "</out>",
|
144 |
-
"single_word": false,
|
145 |
-
"lstrip": false,
|
146 |
-
"rstrip": false,
|
147 |
-
"normalized": false,
|
148 |
-
"special": true
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"id": 50276,
|
152 |
-
"content": "<evidence>",
|
153 |
-
"single_word": false,
|
154 |
-
"lstrip": false,
|
155 |
-
"rstrip": false,
|
156 |
-
"normalized": false,
|
157 |
-
"special": true
|
158 |
-
},
|
159 |
-
{
|
160 |
-
"id": 50277,
|
161 |
-
"content": "</evidence>",
|
162 |
-
"single_word": false,
|
163 |
-
"lstrip": false,
|
164 |
-
"rstrip": false,
|
165 |
-
"normalized": false,
|
166 |
-
"special": true
|
167 |
}
|
168 |
],
|
169 |
"normalizer": null,
|
|
|
47 |
"rstrip": false,
|
48 |
"normalized": true,
|
49 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
}
|
51 |
],
|
52 |
"normalizer": null,
|