Upload tokenizer.json
Browse files- tokenizer.json +243 -0
tokenizer.json
CHANGED
@@ -39,6 +39,249 @@
|
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
{
|
43 |
"id": 31,
|
44 |
"content": "<null_1>",
|
|
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "L",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 5,
|
53 |
+
"content": "A",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 6,
|
62 |
+
"content": "G",
|
63 |
+
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"id": 7,
|
71 |
+
"content": "V",
|
72 |
+
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"normalized": true,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"id": 8,
|
80 |
+
"content": "S",
|
81 |
+
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": false,
|
84 |
+
"normalized": true,
|
85 |
+
"special": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"id": 9,
|
89 |
+
"content": "E",
|
90 |
+
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"normalized": true,
|
94 |
+
"special": false
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"id": 10,
|
98 |
+
"content": "R",
|
99 |
+
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"special": false
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"id": 11,
|
107 |
+
"content": "T",
|
108 |
+
"single_word": false,
|
109 |
+
"lstrip": false,
|
110 |
+
"rstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"special": false
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"id": 12,
|
116 |
+
"content": "I",
|
117 |
+
"single_word": false,
|
118 |
+
"lstrip": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"normalized": true,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"id": 13,
|
125 |
+
"content": "D",
|
126 |
+
"single_word": false,
|
127 |
+
"lstrip": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"id": 14,
|
134 |
+
"content": "P",
|
135 |
+
"single_word": false,
|
136 |
+
"lstrip": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"normalized": true,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"id": 15,
|
143 |
+
"content": "K",
|
144 |
+
"single_word": false,
|
145 |
+
"lstrip": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"normalized": true,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"id": 16,
|
152 |
+
"content": "Q",
|
153 |
+
"single_word": false,
|
154 |
+
"lstrip": false,
|
155 |
+
"rstrip": false,
|
156 |
+
"normalized": true,
|
157 |
+
"special": false
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"id": 17,
|
161 |
+
"content": "N",
|
162 |
+
"single_word": false,
|
163 |
+
"lstrip": false,
|
164 |
+
"rstrip": false,
|
165 |
+
"normalized": true,
|
166 |
+
"special": false
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"id": 18,
|
170 |
+
"content": "F",
|
171 |
+
"single_word": false,
|
172 |
+
"lstrip": false,
|
173 |
+
"rstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"special": false
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"id": 19,
|
179 |
+
"content": "Y",
|
180 |
+
"single_word": false,
|
181 |
+
"lstrip": false,
|
182 |
+
"rstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"special": false
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"id": 20,
|
188 |
+
"content": "M",
|
189 |
+
"single_word": false,
|
190 |
+
"lstrip": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"normalized": true,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"id": 21,
|
197 |
+
"content": "H",
|
198 |
+
"single_word": false,
|
199 |
+
"lstrip": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"id": 22,
|
206 |
+
"content": "W",
|
207 |
+
"single_word": false,
|
208 |
+
"lstrip": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"normalized": true,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"id": 23,
|
215 |
+
"content": "C",
|
216 |
+
"single_word": false,
|
217 |
+
"lstrip": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"normalized": true,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"id": 24,
|
224 |
+
"content": "X",
|
225 |
+
"single_word": false,
|
226 |
+
"lstrip": false,
|
227 |
+
"rstrip": false,
|
228 |
+
"normalized": true,
|
229 |
+
"special": false
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"id": 25,
|
233 |
+
"content": "B",
|
234 |
+
"single_word": false,
|
235 |
+
"lstrip": false,
|
236 |
+
"rstrip": false,
|
237 |
+
"normalized": true,
|
238 |
+
"special": false
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"id": 26,
|
242 |
+
"content": "U",
|
243 |
+
"single_word": false,
|
244 |
+
"lstrip": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"normalized": true,
|
247 |
+
"special": false
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"id": 27,
|
251 |
+
"content": "Z",
|
252 |
+
"single_word": false,
|
253 |
+
"lstrip": false,
|
254 |
+
"rstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"special": false
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"id": 28,
|
260 |
+
"content": "O",
|
261 |
+
"single_word": false,
|
262 |
+
"lstrip": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"normalized": true,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"id": 29,
|
269 |
+
"content": ".",
|
270 |
+
"single_word": false,
|
271 |
+
"lstrip": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"normalized": true,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"id": 30,
|
278 |
+
"content": "-",
|
279 |
+
"single_word": false,
|
280 |
+
"lstrip": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"normalized": true,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
{
|
286 |
"id": 31,
|
287 |
"content": "<null_1>",
|