Upload tokenizer
Browse files- special_tokens_map.json +882 -0
- tokenizer_config.json +379 -253
special_tokens_map.json
CHANGED
@@ -13,6 +13,888 @@
|
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"bos_token": {
|
|
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<|padding_token_0|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "<|padding_token_1|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<|padding_token_2|>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "<|padding_token_3|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<|padding_token_4|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "<|padding_token_5|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"content": "<|padding_token_6|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"content": "<|padding_token_7|>",
|
68 |
+
"lstrip": false,
|
69 |
+
"normalized": false,
|
70 |
+
"rstrip": false,
|
71 |
+
"single_word": false
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"content": "<|padding_token_8|>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": false,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"content": "<|padding_token_9|>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": false,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"content": "<|padding_token_10|>",
|
89 |
+
"lstrip": false,
|
90 |
+
"normalized": false,
|
91 |
+
"rstrip": false,
|
92 |
+
"single_word": false
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"content": "<|padding_token_11|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"content": "<|padding_token_12|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"content": "<|padding_token_13|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"content": "<|padding_token_14|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"content": "<|padding_token_15|>",
|
124 |
+
"lstrip": false,
|
125 |
+
"normalized": false,
|
126 |
+
"rstrip": false,
|
127 |
+
"single_word": false
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"content": "<|padding_token_16|>",
|
131 |
+
"lstrip": false,
|
132 |
+
"normalized": false,
|
133 |
+
"rstrip": false,
|
134 |
+
"single_word": false
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"content": "<|padding_token_17|>",
|
138 |
+
"lstrip": false,
|
139 |
+
"normalized": false,
|
140 |
+
"rstrip": false,
|
141 |
+
"single_word": false
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"content": "<|padding_token_18|>",
|
145 |
+
"lstrip": false,
|
146 |
+
"normalized": false,
|
147 |
+
"rstrip": false,
|
148 |
+
"single_word": false
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"content": "<|padding_token_19|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"content": "<|padding_token_20|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"content": "<|padding_token_21|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"content": "<|padding_token_22|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"content": "<|padding_token_23|>",
|
180 |
+
"lstrip": false,
|
181 |
+
"normalized": false,
|
182 |
+
"rstrip": false,
|
183 |
+
"single_word": false
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"content": "<|padding_token_24|>",
|
187 |
+
"lstrip": false,
|
188 |
+
"normalized": false,
|
189 |
+
"rstrip": false,
|
190 |
+
"single_word": false
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"content": "<|padding_token_25|>",
|
194 |
+
"lstrip": false,
|
195 |
+
"normalized": false,
|
196 |
+
"rstrip": false,
|
197 |
+
"single_word": false
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"content": "<|padding_token_26|>",
|
201 |
+
"lstrip": false,
|
202 |
+
"normalized": false,
|
203 |
+
"rstrip": false,
|
204 |
+
"single_word": false
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"content": "<|padding_token_27|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"content": "<|padding_token_28|>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"content": "<|padding_token_29|>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"content": "<|padding_token_30|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"content": "<|padding_token_31|>",
|
236 |
+
"lstrip": false,
|
237 |
+
"normalized": false,
|
238 |
+
"rstrip": false,
|
239 |
+
"single_word": false
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"content": "<|padding_token_32|>",
|
243 |
+
"lstrip": false,
|
244 |
+
"normalized": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"single_word": false
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"content": "<|padding_token_33|>",
|
250 |
+
"lstrip": false,
|
251 |
+
"normalized": false,
|
252 |
+
"rstrip": false,
|
253 |
+
"single_word": false
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"content": "<|padding_token_34|>",
|
257 |
+
"lstrip": false,
|
258 |
+
"normalized": false,
|
259 |
+
"rstrip": false,
|
260 |
+
"single_word": false
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"content": "<|padding_token_35|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"content": "<|padding_token_36|>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"content": "<|padding_token_37|>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"content": "<|padding_token_38|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"content": "<|padding_token_39|>",
|
292 |
+
"lstrip": false,
|
293 |
+
"normalized": false,
|
294 |
+
"rstrip": false,
|
295 |
+
"single_word": false
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"content": "<|padding_token_40|>",
|
299 |
+
"lstrip": false,
|
300 |
+
"normalized": false,
|
301 |
+
"rstrip": false,
|
302 |
+
"single_word": false
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"content": "<|padding_token_41|>",
|
306 |
+
"lstrip": false,
|
307 |
+
"normalized": false,
|
308 |
+
"rstrip": false,
|
309 |
+
"single_word": false
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"content": "<|padding_token_42|>",
|
313 |
+
"lstrip": false,
|
314 |
+
"normalized": false,
|
315 |
+
"rstrip": false,
|
316 |
+
"single_word": false
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"content": "<|padding_token_43|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"content": "<|padding_token_44|>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"content": "<|padding_token_45|>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"content": "<|padding_token_46|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"content": "<|padding_token_47|>",
|
348 |
+
"lstrip": false,
|
349 |
+
"normalized": false,
|
350 |
+
"rstrip": false,
|
351 |
+
"single_word": false
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"content": "<|padding_token_48|>",
|
355 |
+
"lstrip": false,
|
356 |
+
"normalized": false,
|
357 |
+
"rstrip": false,
|
358 |
+
"single_word": false
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"content": "<|padding_token_49|>",
|
362 |
+
"lstrip": false,
|
363 |
+
"normalized": false,
|
364 |
+
"rstrip": false,
|
365 |
+
"single_word": false
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"content": "<|padding_token_50|>",
|
369 |
+
"lstrip": false,
|
370 |
+
"normalized": false,
|
371 |
+
"rstrip": false,
|
372 |
+
"single_word": false
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"content": "<|padding_token_51|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"content": "<|padding_token_52|>",
|
383 |
+
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"content": "<|padding_token_53|>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"content": "<|padding_token_54|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"content": "<|padding_token_55|>",
|
404 |
+
"lstrip": false,
|
405 |
+
"normalized": false,
|
406 |
+
"rstrip": false,
|
407 |
+
"single_word": false
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"content": "<|padding_token_56|>",
|
411 |
+
"lstrip": false,
|
412 |
+
"normalized": false,
|
413 |
+
"rstrip": false,
|
414 |
+
"single_word": false
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"content": "<|padding_token_57|>",
|
418 |
+
"lstrip": false,
|
419 |
+
"normalized": false,
|
420 |
+
"rstrip": false,
|
421 |
+
"single_word": false
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"content": "<|padding_token_58|>",
|
425 |
+
"lstrip": false,
|
426 |
+
"normalized": false,
|
427 |
+
"rstrip": false,
|
428 |
+
"single_word": false
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"content": "<|padding_token_59|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"content": "<|padding_token_60|>",
|
439 |
+
"lstrip": false,
|
440 |
+
"normalized": false,
|
441 |
+
"rstrip": false,
|
442 |
+
"single_word": false
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"content": "<|padding_token_61|>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"content": "<|padding_token_62|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"content": "<|padding_token_63|>",
|
460 |
+
"lstrip": false,
|
461 |
+
"normalized": false,
|
462 |
+
"rstrip": false,
|
463 |
+
"single_word": false
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"content": "<|padding_token_64|>",
|
467 |
+
"lstrip": false,
|
468 |
+
"normalized": false,
|
469 |
+
"rstrip": false,
|
470 |
+
"single_word": false
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"content": "<|padding_token_65|>",
|
474 |
+
"lstrip": false,
|
475 |
+
"normalized": false,
|
476 |
+
"rstrip": false,
|
477 |
+
"single_word": false
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"content": "<|padding_token_66|>",
|
481 |
+
"lstrip": false,
|
482 |
+
"normalized": false,
|
483 |
+
"rstrip": false,
|
484 |
+
"single_word": false
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"content": "<|padding_token_67|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"content": "<|padding_token_68|>",
|
495 |
+
"lstrip": false,
|
496 |
+
"normalized": false,
|
497 |
+
"rstrip": false,
|
498 |
+
"single_word": false
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"content": "<|padding_token_69|>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"content": "<|padding_token_70|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"content": "<|padding_token_71|>",
|
516 |
+
"lstrip": false,
|
517 |
+
"normalized": false,
|
518 |
+
"rstrip": false,
|
519 |
+
"single_word": false
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"content": "<|padding_token_72|>",
|
523 |
+
"lstrip": false,
|
524 |
+
"normalized": false,
|
525 |
+
"rstrip": false,
|
526 |
+
"single_word": false
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"content": "<|padding_token_73|>",
|
530 |
+
"lstrip": false,
|
531 |
+
"normalized": false,
|
532 |
+
"rstrip": false,
|
533 |
+
"single_word": false
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"content": "<|padding_token_74|>",
|
537 |
+
"lstrip": false,
|
538 |
+
"normalized": false,
|
539 |
+
"rstrip": false,
|
540 |
+
"single_word": false
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"content": "<|padding_token_75|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"content": "<|padding_token_76|>",
|
551 |
+
"lstrip": false,
|
552 |
+
"normalized": false,
|
553 |
+
"rstrip": false,
|
554 |
+
"single_word": false
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"content": "<|padding_token_77|>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"content": "<|padding_token_78|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"content": "<|padding_token_79|>",
|
572 |
+
"lstrip": false,
|
573 |
+
"normalized": false,
|
574 |
+
"rstrip": false,
|
575 |
+
"single_word": false
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"content": "<|padding_token_80|>",
|
579 |
+
"lstrip": false,
|
580 |
+
"normalized": false,
|
581 |
+
"rstrip": false,
|
582 |
+
"single_word": false
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"content": "<|padding_token_81|>",
|
586 |
+
"lstrip": false,
|
587 |
+
"normalized": false,
|
588 |
+
"rstrip": false,
|
589 |
+
"single_word": false
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"content": "<|padding_token_82|>",
|
593 |
+
"lstrip": false,
|
594 |
+
"normalized": false,
|
595 |
+
"rstrip": false,
|
596 |
+
"single_word": false
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"content": "<|padding_token_83|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"content": "<|padding_token_84|>",
|
607 |
+
"lstrip": false,
|
608 |
+
"normalized": false,
|
609 |
+
"rstrip": false,
|
610 |
+
"single_word": false
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"content": "<|padding_token_85|>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"content": "<|padding_token_86|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"content": "<|padding_token_87|>",
|
628 |
+
"lstrip": false,
|
629 |
+
"normalized": false,
|
630 |
+
"rstrip": false,
|
631 |
+
"single_word": false
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"content": "<|padding_token_88|>",
|
635 |
+
"lstrip": false,
|
636 |
+
"normalized": false,
|
637 |
+
"rstrip": false,
|
638 |
+
"single_word": false
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"content": "<|padding_token_89|>",
|
642 |
+
"lstrip": false,
|
643 |
+
"normalized": false,
|
644 |
+
"rstrip": false,
|
645 |
+
"single_word": false
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"content": "<|padding_token_90|>",
|
649 |
+
"lstrip": false,
|
650 |
+
"normalized": false,
|
651 |
+
"rstrip": false,
|
652 |
+
"single_word": false
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"content": "<|padding_token_91|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"content": "<|padding_token_92|>",
|
663 |
+
"lstrip": false,
|
664 |
+
"normalized": false,
|
665 |
+
"rstrip": false,
|
666 |
+
"single_word": false
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"content": "<|padding_token_93|>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"content": "<|padding_token_94|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"content": "<|padding_token_95|>",
|
684 |
+
"lstrip": false,
|
685 |
+
"normalized": false,
|
686 |
+
"rstrip": false,
|
687 |
+
"single_word": false
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"content": "<|padding_token_96|>",
|
691 |
+
"lstrip": false,
|
692 |
+
"normalized": false,
|
693 |
+
"rstrip": false,
|
694 |
+
"single_word": false
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"content": "<|padding_token_97|>",
|
698 |
+
"lstrip": false,
|
699 |
+
"normalized": false,
|
700 |
+
"rstrip": false,
|
701 |
+
"single_word": false
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"content": "<|padding_token_98|>",
|
705 |
+
"lstrip": false,
|
706 |
+
"normalized": false,
|
707 |
+
"rstrip": false,
|
708 |
+
"single_word": false
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"content": "<|padding_token_99|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"content": "<|padding_token_100|>",
|
719 |
+
"lstrip": false,
|
720 |
+
"normalized": false,
|
721 |
+
"rstrip": false,
|
722 |
+
"single_word": false
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"content": "<|padding_token_101|>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"content": "<|padding_token_102|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"content": "<|padding_token_103|>",
|
740 |
+
"lstrip": false,
|
741 |
+
"normalized": false,
|
742 |
+
"rstrip": false,
|
743 |
+
"single_word": false
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"content": "<|padding_token_104|>",
|
747 |
+
"lstrip": false,
|
748 |
+
"normalized": false,
|
749 |
+
"rstrip": false,
|
750 |
+
"single_word": false
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"content": "<|padding_token_105|>",
|
754 |
+
"lstrip": false,
|
755 |
+
"normalized": false,
|
756 |
+
"rstrip": false,
|
757 |
+
"single_word": false
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"content": "<|padding_token_106|>",
|
761 |
+
"lstrip": false,
|
762 |
+
"normalized": false,
|
763 |
+
"rstrip": false,
|
764 |
+
"single_word": false
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"content": "<|padding_token_107|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"content": "<|padding_token_108|>",
|
775 |
+
"lstrip": false,
|
776 |
+
"normalized": false,
|
777 |
+
"rstrip": false,
|
778 |
+
"single_word": false
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"content": "<|padding_token_109|>",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"content": "<|padding_token_110|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"content": "<|padding_token_111|>",
|
796 |
+
"lstrip": false,
|
797 |
+
"normalized": false,
|
798 |
+
"rstrip": false,
|
799 |
+
"single_word": false
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"content": "<|padding_token_112|>",
|
803 |
+
"lstrip": false,
|
804 |
+
"normalized": false,
|
805 |
+
"rstrip": false,
|
806 |
+
"single_word": false
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"content": "<|padding_token_113|>",
|
810 |
+
"lstrip": false,
|
811 |
+
"normalized": false,
|
812 |
+
"rstrip": false,
|
813 |
+
"single_word": false
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"content": "<|padding_token_114|>",
|
817 |
+
"lstrip": false,
|
818 |
+
"normalized": false,
|
819 |
+
"rstrip": false,
|
820 |
+
"single_word": false
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"content": "<|padding_token_115|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"content": "<|padding_token_116|>",
|
831 |
+
"lstrip": false,
|
832 |
+
"normalized": false,
|
833 |
+
"rstrip": false,
|
834 |
+
"single_word": false
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"content": "<|padding_token_117|>",
|
838 |
+
"lstrip": false,
|
839 |
+
"normalized": false,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"content": "<|padding_token_118|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"content": "<|padding_token_119|>",
|
852 |
+
"lstrip": false,
|
853 |
+
"normalized": false,
|
854 |
+
"rstrip": false,
|
855 |
+
"single_word": false
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"content": "<|padding_token_120|>",
|
859 |
+
"lstrip": false,
|
860 |
+
"normalized": false,
|
861 |
+
"rstrip": false,
|
862 |
+
"single_word": false
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"content": "<|padding_token_121|>",
|
866 |
+
"lstrip": false,
|
867 |
+
"normalized": false,
|
868 |
+
"rstrip": false,
|
869 |
+
"single_word": false
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"content": "<|padding_token_122|>",
|
873 |
+
"lstrip": false,
|
874 |
+
"normalized": false,
|
875 |
+
"rstrip": false,
|
876 |
+
"single_word": false
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"content": "<|padding_token_123|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"content": "<|padding_token_124|>",
|
887 |
+
"lstrip": false,
|
888 |
+
"normalized": false,
|
889 |
+
"rstrip": false,
|
890 |
+
"single_word": false
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"content": "<|padding_token_125|>",
|
894 |
+
"lstrip": false,
|
895 |
+
"normalized": false,
|
896 |
+
"rstrip": false,
|
897 |
+
"single_word": false
|
898 |
}
|
899 |
],
|
900 |
"bos_token": {
|
tokenizer_config.json
CHANGED
@@ -45,1015 +45,1141 @@
|
|
45 |
"32002": {
|
46 |
"content": "<|padding_token_0|>",
|
47 |
"lstrip": false,
|
48 |
-
"normalized":
|
49 |
"rstrip": false,
|
50 |
"single_word": false,
|
51 |
-
"special":
|
52 |
},
|
53 |
"32003": {
|
54 |
"content": "<|padding_token_1|>",
|
55 |
"lstrip": false,
|
56 |
-
"normalized":
|
57 |
"rstrip": false,
|
58 |
"single_word": false,
|
59 |
-
"special":
|
60 |
},
|
61 |
"32004": {
|
62 |
"content": "<|padding_token_2|>",
|
63 |
"lstrip": false,
|
64 |
-
"normalized":
|
65 |
"rstrip": false,
|
66 |
"single_word": false,
|
67 |
-
"special":
|
68 |
},
|
69 |
"32005": {
|
70 |
"content": "<|padding_token_3|>",
|
71 |
"lstrip": false,
|
72 |
-
"normalized":
|
73 |
"rstrip": false,
|
74 |
"single_word": false,
|
75 |
-
"special":
|
76 |
},
|
77 |
"32006": {
|
78 |
"content": "<|padding_token_4|>",
|
79 |
"lstrip": false,
|
80 |
-
"normalized":
|
81 |
"rstrip": false,
|
82 |
"single_word": false,
|
83 |
-
"special":
|
84 |
},
|
85 |
"32007": {
|
86 |
"content": "<|padding_token_5|>",
|
87 |
"lstrip": false,
|
88 |
-
"normalized":
|
89 |
"rstrip": false,
|
90 |
"single_word": false,
|
91 |
-
"special":
|
92 |
},
|
93 |
"32008": {
|
94 |
"content": "<|padding_token_6|>",
|
95 |
"lstrip": false,
|
96 |
-
"normalized":
|
97 |
"rstrip": false,
|
98 |
"single_word": false,
|
99 |
-
"special":
|
100 |
},
|
101 |
"32009": {
|
102 |
"content": "<|padding_token_7|>",
|
103 |
"lstrip": false,
|
104 |
-
"normalized":
|
105 |
"rstrip": false,
|
106 |
"single_word": false,
|
107 |
-
"special":
|
108 |
},
|
109 |
"32010": {
|
110 |
"content": "<|padding_token_8|>",
|
111 |
"lstrip": false,
|
112 |
-
"normalized":
|
113 |
"rstrip": false,
|
114 |
"single_word": false,
|
115 |
-
"special":
|
116 |
},
|
117 |
"32011": {
|
118 |
"content": "<|padding_token_9|>",
|
119 |
"lstrip": false,
|
120 |
-
"normalized":
|
121 |
"rstrip": false,
|
122 |
"single_word": false,
|
123 |
-
"special":
|
124 |
},
|
125 |
"32012": {
|
126 |
"content": "<|padding_token_10|>",
|
127 |
"lstrip": false,
|
128 |
-
"normalized":
|
129 |
"rstrip": false,
|
130 |
"single_word": false,
|
131 |
-
"special":
|
132 |
},
|
133 |
"32013": {
|
134 |
"content": "<|padding_token_11|>",
|
135 |
"lstrip": false,
|
136 |
-
"normalized":
|
137 |
"rstrip": false,
|
138 |
"single_word": false,
|
139 |
-
"special":
|
140 |
},
|
141 |
"32014": {
|
142 |
"content": "<|padding_token_12|>",
|
143 |
"lstrip": false,
|
144 |
-
"normalized":
|
145 |
"rstrip": false,
|
146 |
"single_word": false,
|
147 |
-
"special":
|
148 |
},
|
149 |
"32015": {
|
150 |
"content": "<|padding_token_13|>",
|
151 |
"lstrip": false,
|
152 |
-
"normalized":
|
153 |
"rstrip": false,
|
154 |
"single_word": false,
|
155 |
-
"special":
|
156 |
},
|
157 |
"32016": {
|
158 |
"content": "<|padding_token_14|>",
|
159 |
"lstrip": false,
|
160 |
-
"normalized":
|
161 |
"rstrip": false,
|
162 |
"single_word": false,
|
163 |
-
"special":
|
164 |
},
|
165 |
"32017": {
|
166 |
"content": "<|padding_token_15|>",
|
167 |
"lstrip": false,
|
168 |
-
"normalized":
|
169 |
"rstrip": false,
|
170 |
"single_word": false,
|
171 |
-
"special":
|
172 |
},
|
173 |
"32018": {
|
174 |
"content": "<|padding_token_16|>",
|
175 |
"lstrip": false,
|
176 |
-
"normalized":
|
177 |
"rstrip": false,
|
178 |
"single_word": false,
|
179 |
-
"special":
|
180 |
},
|
181 |
"32019": {
|
182 |
"content": "<|padding_token_17|>",
|
183 |
"lstrip": false,
|
184 |
-
"normalized":
|
185 |
"rstrip": false,
|
186 |
"single_word": false,
|
187 |
-
"special":
|
188 |
},
|
189 |
"32020": {
|
190 |
"content": "<|padding_token_18|>",
|
191 |
"lstrip": false,
|
192 |
-
"normalized":
|
193 |
"rstrip": false,
|
194 |
"single_word": false,
|
195 |
-
"special":
|
196 |
},
|
197 |
"32021": {
|
198 |
"content": "<|padding_token_19|>",
|
199 |
"lstrip": false,
|
200 |
-
"normalized":
|
201 |
"rstrip": false,
|
202 |
"single_word": false,
|
203 |
-
"special":
|
204 |
},
|
205 |
"32022": {
|
206 |
"content": "<|padding_token_20|>",
|
207 |
"lstrip": false,
|
208 |
-
"normalized":
|
209 |
"rstrip": false,
|
210 |
"single_word": false,
|
211 |
-
"special":
|
212 |
},
|
213 |
"32023": {
|
214 |
"content": "<|padding_token_21|>",
|
215 |
"lstrip": false,
|
216 |
-
"normalized":
|
217 |
"rstrip": false,
|
218 |
"single_word": false,
|
219 |
-
"special":
|
220 |
},
|
221 |
"32024": {
|
222 |
"content": "<|padding_token_22|>",
|
223 |
"lstrip": false,
|
224 |
-
"normalized":
|
225 |
"rstrip": false,
|
226 |
"single_word": false,
|
227 |
-
"special":
|
228 |
},
|
229 |
"32025": {
|
230 |
"content": "<|padding_token_23|>",
|
231 |
"lstrip": false,
|
232 |
-
"normalized":
|
233 |
"rstrip": false,
|
234 |
"single_word": false,
|
235 |
-
"special":
|
236 |
},
|
237 |
"32026": {
|
238 |
"content": "<|padding_token_24|>",
|
239 |
"lstrip": false,
|
240 |
-
"normalized":
|
241 |
"rstrip": false,
|
242 |
"single_word": false,
|
243 |
-
"special":
|
244 |
},
|
245 |
"32027": {
|
246 |
"content": "<|padding_token_25|>",
|
247 |
"lstrip": false,
|
248 |
-
"normalized":
|
249 |
"rstrip": false,
|
250 |
"single_word": false,
|
251 |
-
"special":
|
252 |
},
|
253 |
"32028": {
|
254 |
"content": "<|padding_token_26|>",
|
255 |
"lstrip": false,
|
256 |
-
"normalized":
|
257 |
"rstrip": false,
|
258 |
"single_word": false,
|
259 |
-
"special":
|
260 |
},
|
261 |
"32029": {
|
262 |
"content": "<|padding_token_27|>",
|
263 |
"lstrip": false,
|
264 |
-
"normalized":
|
265 |
"rstrip": false,
|
266 |
"single_word": false,
|
267 |
-
"special":
|
268 |
},
|
269 |
"32030": {
|
270 |
"content": "<|padding_token_28|>",
|
271 |
"lstrip": false,
|
272 |
-
"normalized":
|
273 |
"rstrip": false,
|
274 |
"single_word": false,
|
275 |
-
"special":
|
276 |
},
|
277 |
"32031": {
|
278 |
"content": "<|padding_token_29|>",
|
279 |
"lstrip": false,
|
280 |
-
"normalized":
|
281 |
"rstrip": false,
|
282 |
"single_word": false,
|
283 |
-
"special":
|
284 |
},
|
285 |
"32032": {
|
286 |
"content": "<|padding_token_30|>",
|
287 |
"lstrip": false,
|
288 |
-
"normalized":
|
289 |
"rstrip": false,
|
290 |
"single_word": false,
|
291 |
-
"special":
|
292 |
},
|
293 |
"32033": {
|
294 |
"content": "<|padding_token_31|>",
|
295 |
"lstrip": false,
|
296 |
-
"normalized":
|
297 |
"rstrip": false,
|
298 |
"single_word": false,
|
299 |
-
"special":
|
300 |
},
|
301 |
"32034": {
|
302 |
"content": "<|padding_token_32|>",
|
303 |
"lstrip": false,
|
304 |
-
"normalized":
|
305 |
"rstrip": false,
|
306 |
"single_word": false,
|
307 |
-
"special":
|
308 |
},
|
309 |
"32035": {
|
310 |
"content": "<|padding_token_33|>",
|
311 |
"lstrip": false,
|
312 |
-
"normalized":
|
313 |
"rstrip": false,
|
314 |
"single_word": false,
|
315 |
-
"special":
|
316 |
},
|
317 |
"32036": {
|
318 |
"content": "<|padding_token_34|>",
|
319 |
"lstrip": false,
|
320 |
-
"normalized":
|
321 |
"rstrip": false,
|
322 |
"single_word": false,
|
323 |
-
"special":
|
324 |
},
|
325 |
"32037": {
|
326 |
"content": "<|padding_token_35|>",
|
327 |
"lstrip": false,
|
328 |
-
"normalized":
|
329 |
"rstrip": false,
|
330 |
"single_word": false,
|
331 |
-
"special":
|
332 |
},
|
333 |
"32038": {
|
334 |
"content": "<|padding_token_36|>",
|
335 |
"lstrip": false,
|
336 |
-
"normalized":
|
337 |
"rstrip": false,
|
338 |
"single_word": false,
|
339 |
-
"special":
|
340 |
},
|
341 |
"32039": {
|
342 |
"content": "<|padding_token_37|>",
|
343 |
"lstrip": false,
|
344 |
-
"normalized":
|
345 |
"rstrip": false,
|
346 |
"single_word": false,
|
347 |
-
"special":
|
348 |
},
|
349 |
"32040": {
|
350 |
"content": "<|padding_token_38|>",
|
351 |
"lstrip": false,
|
352 |
-
"normalized":
|
353 |
"rstrip": false,
|
354 |
"single_word": false,
|
355 |
-
"special":
|
356 |
},
|
357 |
"32041": {
|
358 |
"content": "<|padding_token_39|>",
|
359 |
"lstrip": false,
|
360 |
-
"normalized":
|
361 |
"rstrip": false,
|
362 |
"single_word": false,
|
363 |
-
"special":
|
364 |
},
|
365 |
"32042": {
|
366 |
"content": "<|padding_token_40|>",
|
367 |
"lstrip": false,
|
368 |
-
"normalized":
|
369 |
"rstrip": false,
|
370 |
"single_word": false,
|
371 |
-
"special":
|
372 |
},
|
373 |
"32043": {
|
374 |
"content": "<|padding_token_41|>",
|
375 |
"lstrip": false,
|
376 |
-
"normalized":
|
377 |
"rstrip": false,
|
378 |
"single_word": false,
|
379 |
-
"special":
|
380 |
},
|
381 |
"32044": {
|
382 |
"content": "<|padding_token_42|>",
|
383 |
"lstrip": false,
|
384 |
-
"normalized":
|
385 |
"rstrip": false,
|
386 |
"single_word": false,
|
387 |
-
"special":
|
388 |
},
|
389 |
"32045": {
|
390 |
"content": "<|padding_token_43|>",
|
391 |
"lstrip": false,
|
392 |
-
"normalized":
|
393 |
"rstrip": false,
|
394 |
"single_word": false,
|
395 |
-
"special":
|
396 |
},
|
397 |
"32046": {
|
398 |
"content": "<|padding_token_44|>",
|
399 |
"lstrip": false,
|
400 |
-
"normalized":
|
401 |
"rstrip": false,
|
402 |
"single_word": false,
|
403 |
-
"special":
|
404 |
},
|
405 |
"32047": {
|
406 |
"content": "<|padding_token_45|>",
|
407 |
"lstrip": false,
|
408 |
-
"normalized":
|
409 |
"rstrip": false,
|
410 |
"single_word": false,
|
411 |
-
"special":
|
412 |
},
|
413 |
"32048": {
|
414 |
"content": "<|padding_token_46|>",
|
415 |
"lstrip": false,
|
416 |
-
"normalized":
|
417 |
"rstrip": false,
|
418 |
"single_word": false,
|
419 |
-
"special":
|
420 |
},
|
421 |
"32049": {
|
422 |
"content": "<|padding_token_47|>",
|
423 |
"lstrip": false,
|
424 |
-
"normalized":
|
425 |
"rstrip": false,
|
426 |
"single_word": false,
|
427 |
-
"special":
|
428 |
},
|
429 |
"32050": {
|
430 |
"content": "<|padding_token_48|>",
|
431 |
"lstrip": false,
|
432 |
-
"normalized":
|
433 |
"rstrip": false,
|
434 |
"single_word": false,
|
435 |
-
"special":
|
436 |
},
|
437 |
"32051": {
|
438 |
"content": "<|padding_token_49|>",
|
439 |
"lstrip": false,
|
440 |
-
"normalized":
|
441 |
"rstrip": false,
|
442 |
"single_word": false,
|
443 |
-
"special":
|
444 |
},
|
445 |
"32052": {
|
446 |
"content": "<|padding_token_50|>",
|
447 |
"lstrip": false,
|
448 |
-
"normalized":
|
449 |
"rstrip": false,
|
450 |
"single_word": false,
|
451 |
-
"special":
|
452 |
},
|
453 |
"32053": {
|
454 |
"content": "<|padding_token_51|>",
|
455 |
"lstrip": false,
|
456 |
-
"normalized":
|
457 |
"rstrip": false,
|
458 |
"single_word": false,
|
459 |
-
"special":
|
460 |
},
|
461 |
"32054": {
|
462 |
"content": "<|padding_token_52|>",
|
463 |
"lstrip": false,
|
464 |
-
"normalized":
|
465 |
"rstrip": false,
|
466 |
"single_word": false,
|
467 |
-
"special":
|
468 |
},
|
469 |
"32055": {
|
470 |
"content": "<|padding_token_53|>",
|
471 |
"lstrip": false,
|
472 |
-
"normalized":
|
473 |
"rstrip": false,
|
474 |
"single_word": false,
|
475 |
-
"special":
|
476 |
},
|
477 |
"32056": {
|
478 |
"content": "<|padding_token_54|>",
|
479 |
"lstrip": false,
|
480 |
-
"normalized":
|
481 |
"rstrip": false,
|
482 |
"single_word": false,
|
483 |
-
"special":
|
484 |
},
|
485 |
"32057": {
|
486 |
"content": "<|padding_token_55|>",
|
487 |
"lstrip": false,
|
488 |
-
"normalized":
|
489 |
"rstrip": false,
|
490 |
"single_word": false,
|
491 |
-
"special":
|
492 |
},
|
493 |
"32058": {
|
494 |
"content": "<|padding_token_56|>",
|
495 |
"lstrip": false,
|
496 |
-
"normalized":
|
497 |
"rstrip": false,
|
498 |
"single_word": false,
|
499 |
-
"special":
|
500 |
},
|
501 |
"32059": {
|
502 |
"content": "<|padding_token_57|>",
|
503 |
"lstrip": false,
|
504 |
-
"normalized":
|
505 |
"rstrip": false,
|
506 |
"single_word": false,
|
507 |
-
"special":
|
508 |
},
|
509 |
"32060": {
|
510 |
"content": "<|padding_token_58|>",
|
511 |
"lstrip": false,
|
512 |
-
"normalized":
|
513 |
"rstrip": false,
|
514 |
"single_word": false,
|
515 |
-
"special":
|
516 |
},
|
517 |
"32061": {
|
518 |
"content": "<|padding_token_59|>",
|
519 |
"lstrip": false,
|
520 |
-
"normalized":
|
521 |
"rstrip": false,
|
522 |
"single_word": false,
|
523 |
-
"special":
|
524 |
},
|
525 |
"32062": {
|
526 |
"content": "<|padding_token_60|>",
|
527 |
"lstrip": false,
|
528 |
-
"normalized":
|
529 |
"rstrip": false,
|
530 |
"single_word": false,
|
531 |
-
"special":
|
532 |
},
|
533 |
"32063": {
|
534 |
"content": "<|padding_token_61|>",
|
535 |
"lstrip": false,
|
536 |
-
"normalized":
|
537 |
"rstrip": false,
|
538 |
"single_word": false,
|
539 |
-
"special":
|
540 |
},
|
541 |
"32064": {
|
542 |
"content": "<|padding_token_62|>",
|
543 |
"lstrip": false,
|
544 |
-
"normalized":
|
545 |
"rstrip": false,
|
546 |
"single_word": false,
|
547 |
-
"special":
|
548 |
},
|
549 |
"32065": {
|
550 |
"content": "<|padding_token_63|>",
|
551 |
"lstrip": false,
|
552 |
-
"normalized":
|
553 |
"rstrip": false,
|
554 |
"single_word": false,
|
555 |
-
"special":
|
556 |
},
|
557 |
"32066": {
|
558 |
"content": "<|padding_token_64|>",
|
559 |
"lstrip": false,
|
560 |
-
"normalized":
|
561 |
"rstrip": false,
|
562 |
"single_word": false,
|
563 |
-
"special":
|
564 |
},
|
565 |
"32067": {
|
566 |
"content": "<|padding_token_65|>",
|
567 |
"lstrip": false,
|
568 |
-
"normalized":
|
569 |
"rstrip": false,
|
570 |
"single_word": false,
|
571 |
-
"special":
|
572 |
},
|
573 |
"32068": {
|
574 |
"content": "<|padding_token_66|>",
|
575 |
"lstrip": false,
|
576 |
-
"normalized":
|
577 |
"rstrip": false,
|
578 |
"single_word": false,
|
579 |
-
"special":
|
580 |
},
|
581 |
"32069": {
|
582 |
"content": "<|padding_token_67|>",
|
583 |
"lstrip": false,
|
584 |
-
"normalized":
|
585 |
"rstrip": false,
|
586 |
"single_word": false,
|
587 |
-
"special":
|
588 |
},
|
589 |
"32070": {
|
590 |
"content": "<|padding_token_68|>",
|
591 |
"lstrip": false,
|
592 |
-
"normalized":
|
593 |
"rstrip": false,
|
594 |
"single_word": false,
|
595 |
-
"special":
|
596 |
},
|
597 |
"32071": {
|
598 |
"content": "<|padding_token_69|>",
|
599 |
"lstrip": false,
|
600 |
-
"normalized":
|
601 |
"rstrip": false,
|
602 |
"single_word": false,
|
603 |
-
"special":
|
604 |
},
|
605 |
"32072": {
|
606 |
"content": "<|padding_token_70|>",
|
607 |
"lstrip": false,
|
608 |
-
"normalized":
|
609 |
"rstrip": false,
|
610 |
"single_word": false,
|
611 |
-
"special":
|
612 |
},
|
613 |
"32073": {
|
614 |
"content": "<|padding_token_71|>",
|
615 |
"lstrip": false,
|
616 |
-
"normalized":
|
617 |
"rstrip": false,
|
618 |
"single_word": false,
|
619 |
-
"special":
|
620 |
},
|
621 |
"32074": {
|
622 |
"content": "<|padding_token_72|>",
|
623 |
"lstrip": false,
|
624 |
-
"normalized":
|
625 |
"rstrip": false,
|
626 |
"single_word": false,
|
627 |
-
"special":
|
628 |
},
|
629 |
"32075": {
|
630 |
"content": "<|padding_token_73|>",
|
631 |
"lstrip": false,
|
632 |
-
"normalized":
|
633 |
"rstrip": false,
|
634 |
"single_word": false,
|
635 |
-
"special":
|
636 |
},
|
637 |
"32076": {
|
638 |
"content": "<|padding_token_74|>",
|
639 |
"lstrip": false,
|
640 |
-
"normalized":
|
641 |
"rstrip": false,
|
642 |
"single_word": false,
|
643 |
-
"special":
|
644 |
},
|
645 |
"32077": {
|
646 |
"content": "<|padding_token_75|>",
|
647 |
"lstrip": false,
|
648 |
-
"normalized":
|
649 |
"rstrip": false,
|
650 |
"single_word": false,
|
651 |
-
"special":
|
652 |
},
|
653 |
"32078": {
|
654 |
"content": "<|padding_token_76|>",
|
655 |
"lstrip": false,
|
656 |
-
"normalized":
|
657 |
"rstrip": false,
|
658 |
"single_word": false,
|
659 |
-
"special":
|
660 |
},
|
661 |
"32079": {
|
662 |
"content": "<|padding_token_77|>",
|
663 |
"lstrip": false,
|
664 |
-
"normalized":
|
665 |
"rstrip": false,
|
666 |
"single_word": false,
|
667 |
-
"special":
|
668 |
},
|
669 |
"32080": {
|
670 |
"content": "<|padding_token_78|>",
|
671 |
"lstrip": false,
|
672 |
-
"normalized":
|
673 |
"rstrip": false,
|
674 |
"single_word": false,
|
675 |
-
"special":
|
676 |
},
|
677 |
"32081": {
|
678 |
"content": "<|padding_token_79|>",
|
679 |
"lstrip": false,
|
680 |
-
"normalized":
|
681 |
"rstrip": false,
|
682 |
"single_word": false,
|
683 |
-
"special":
|
684 |
},
|
685 |
"32082": {
|
686 |
"content": "<|padding_token_80|>",
|
687 |
"lstrip": false,
|
688 |
-
"normalized":
|
689 |
"rstrip": false,
|
690 |
"single_word": false,
|
691 |
-
"special":
|
692 |
},
|
693 |
"32083": {
|
694 |
"content": "<|padding_token_81|>",
|
695 |
"lstrip": false,
|
696 |
-
"normalized":
|
697 |
"rstrip": false,
|
698 |
"single_word": false,
|
699 |
-
"special":
|
700 |
},
|
701 |
"32084": {
|
702 |
"content": "<|padding_token_82|>",
|
703 |
"lstrip": false,
|
704 |
-
"normalized":
|
705 |
"rstrip": false,
|
706 |
"single_word": false,
|
707 |
-
"special":
|
708 |
},
|
709 |
"32085": {
|
710 |
"content": "<|padding_token_83|>",
|
711 |
"lstrip": false,
|
712 |
-
"normalized":
|
713 |
"rstrip": false,
|
714 |
"single_word": false,
|
715 |
-
"special":
|
716 |
},
|
717 |
"32086": {
|
718 |
"content": "<|padding_token_84|>",
|
719 |
"lstrip": false,
|
720 |
-
"normalized":
|
721 |
"rstrip": false,
|
722 |
"single_word": false,
|
723 |
-
"special":
|
724 |
},
|
725 |
"32087": {
|
726 |
"content": "<|padding_token_85|>",
|
727 |
"lstrip": false,
|
728 |
-
"normalized":
|
729 |
"rstrip": false,
|
730 |
"single_word": false,
|
731 |
-
"special":
|
732 |
},
|
733 |
"32088": {
|
734 |
"content": "<|padding_token_86|>",
|
735 |
"lstrip": false,
|
736 |
-
"normalized":
|
737 |
"rstrip": false,
|
738 |
"single_word": false,
|
739 |
-
"special":
|
740 |
},
|
741 |
"32089": {
|
742 |
"content": "<|padding_token_87|>",
|
743 |
"lstrip": false,
|
744 |
-
"normalized":
|
745 |
"rstrip": false,
|
746 |
"single_word": false,
|
747 |
-
"special":
|
748 |
},
|
749 |
"32090": {
|
750 |
"content": "<|padding_token_88|>",
|
751 |
"lstrip": false,
|
752 |
-
"normalized":
|
753 |
"rstrip": false,
|
754 |
"single_word": false,
|
755 |
-
"special":
|
756 |
},
|
757 |
"32091": {
|
758 |
"content": "<|padding_token_89|>",
|
759 |
"lstrip": false,
|
760 |
-
"normalized":
|
761 |
"rstrip": false,
|
762 |
"single_word": false,
|
763 |
-
"special":
|
764 |
},
|
765 |
"32092": {
|
766 |
"content": "<|padding_token_90|>",
|
767 |
"lstrip": false,
|
768 |
-
"normalized":
|
769 |
"rstrip": false,
|
770 |
"single_word": false,
|
771 |
-
"special":
|
772 |
},
|
773 |
"32093": {
|
774 |
"content": "<|padding_token_91|>",
|
775 |
"lstrip": false,
|
776 |
-
"normalized":
|
777 |
"rstrip": false,
|
778 |
"single_word": false,
|
779 |
-
"special":
|
780 |
},
|
781 |
"32094": {
|
782 |
"content": "<|padding_token_92|>",
|
783 |
"lstrip": false,
|
784 |
-
"normalized":
|
785 |
"rstrip": false,
|
786 |
"single_word": false,
|
787 |
-
"special":
|
788 |
},
|
789 |
"32095": {
|
790 |
"content": "<|padding_token_93|>",
|
791 |
"lstrip": false,
|
792 |
-
"normalized":
|
793 |
"rstrip": false,
|
794 |
"single_word": false,
|
795 |
-
"special":
|
796 |
},
|
797 |
"32096": {
|
798 |
"content": "<|padding_token_94|>",
|
799 |
"lstrip": false,
|
800 |
-
"normalized":
|
801 |
"rstrip": false,
|
802 |
"single_word": false,
|
803 |
-
"special":
|
804 |
},
|
805 |
"32097": {
|
806 |
"content": "<|padding_token_95|>",
|
807 |
"lstrip": false,
|
808 |
-
"normalized":
|
809 |
"rstrip": false,
|
810 |
"single_word": false,
|
811 |
-
"special":
|
812 |
},
|
813 |
"32098": {
|
814 |
"content": "<|padding_token_96|>",
|
815 |
"lstrip": false,
|
816 |
-
"normalized":
|
817 |
"rstrip": false,
|
818 |
"single_word": false,
|
819 |
-
"special":
|
820 |
},
|
821 |
"32099": {
|
822 |
"content": "<|padding_token_97|>",
|
823 |
"lstrip": false,
|
824 |
-
"normalized":
|
825 |
"rstrip": false,
|
826 |
"single_word": false,
|
827 |
-
"special":
|
828 |
},
|
829 |
"32100": {
|
830 |
"content": "<|padding_token_98|>",
|
831 |
"lstrip": false,
|
832 |
-
"normalized":
|
833 |
"rstrip": false,
|
834 |
"single_word": false,
|
835 |
-
"special":
|
836 |
},
|
837 |
"32101": {
|
838 |
"content": "<|padding_token_99|>",
|
839 |
"lstrip": false,
|
840 |
-
"normalized":
|
841 |
"rstrip": false,
|
842 |
"single_word": false,
|
843 |
-
"special":
|
844 |
},
|
845 |
"32102": {
|
846 |
"content": "<|padding_token_100|>",
|
847 |
"lstrip": false,
|
848 |
-
"normalized":
|
849 |
"rstrip": false,
|
850 |
"single_word": false,
|
851 |
-
"special":
|
852 |
},
|
853 |
"32103": {
|
854 |
"content": "<|padding_token_101|>",
|
855 |
"lstrip": false,
|
856 |
-
"normalized":
|
857 |
"rstrip": false,
|
858 |
"single_word": false,
|
859 |
-
"special":
|
860 |
},
|
861 |
"32104": {
|
862 |
"content": "<|padding_token_102|>",
|
863 |
"lstrip": false,
|
864 |
-
"normalized":
|
865 |
"rstrip": false,
|
866 |
"single_word": false,
|
867 |
-
"special":
|
868 |
},
|
869 |
"32105": {
|
870 |
"content": "<|padding_token_103|>",
|
871 |
"lstrip": false,
|
872 |
-
"normalized":
|
873 |
"rstrip": false,
|
874 |
"single_word": false,
|
875 |
-
"special":
|
876 |
},
|
877 |
"32106": {
|
878 |
"content": "<|padding_token_104|>",
|
879 |
"lstrip": false,
|
880 |
-
"normalized":
|
881 |
"rstrip": false,
|
882 |
"single_word": false,
|
883 |
-
"special":
|
884 |
},
|
885 |
"32107": {
|
886 |
"content": "<|padding_token_105|>",
|
887 |
"lstrip": false,
|
888 |
-
"normalized":
|
889 |
"rstrip": false,
|
890 |
"single_word": false,
|
891 |
-
"special":
|
892 |
},
|
893 |
"32108": {
|
894 |
"content": "<|padding_token_106|>",
|
895 |
"lstrip": false,
|
896 |
-
"normalized":
|
897 |
"rstrip": false,
|
898 |
"single_word": false,
|
899 |
-
"special":
|
900 |
},
|
901 |
"32109": {
|
902 |
"content": "<|padding_token_107|>",
|
903 |
"lstrip": false,
|
904 |
-
"normalized":
|
905 |
"rstrip": false,
|
906 |
"single_word": false,
|
907 |
-
"special":
|
908 |
},
|
909 |
"32110": {
|
910 |
"content": "<|padding_token_108|>",
|
911 |
"lstrip": false,
|
912 |
-
"normalized":
|
913 |
"rstrip": false,
|
914 |
"single_word": false,
|
915 |
-
"special":
|
916 |
},
|
917 |
"32111": {
|
918 |
"content": "<|padding_token_109|>",
|
919 |
"lstrip": false,
|
920 |
-
"normalized":
|
921 |
"rstrip": false,
|
922 |
"single_word": false,
|
923 |
-
"special":
|
924 |
},
|
925 |
"32112": {
|
926 |
"content": "<|padding_token_110|>",
|
927 |
"lstrip": false,
|
928 |
-
"normalized":
|
929 |
"rstrip": false,
|
930 |
"single_word": false,
|
931 |
-
"special":
|
932 |
},
|
933 |
"32113": {
|
934 |
"content": "<|padding_token_111|>",
|
935 |
"lstrip": false,
|
936 |
-
"normalized":
|
937 |
"rstrip": false,
|
938 |
"single_word": false,
|
939 |
-
"special":
|
940 |
},
|
941 |
"32114": {
|
942 |
"content": "<|padding_token_112|>",
|
943 |
"lstrip": false,
|
944 |
-
"normalized":
|
945 |
"rstrip": false,
|
946 |
"single_word": false,
|
947 |
-
"special":
|
948 |
},
|
949 |
"32115": {
|
950 |
"content": "<|padding_token_113|>",
|
951 |
"lstrip": false,
|
952 |
-
"normalized":
|
953 |
"rstrip": false,
|
954 |
"single_word": false,
|
955 |
-
"special":
|
956 |
},
|
957 |
"32116": {
|
958 |
"content": "<|padding_token_114|>",
|
959 |
"lstrip": false,
|
960 |
-
"normalized":
|
961 |
"rstrip": false,
|
962 |
"single_word": false,
|
963 |
-
"special":
|
964 |
},
|
965 |
"32117": {
|
966 |
"content": "<|padding_token_115|>",
|
967 |
"lstrip": false,
|
968 |
-
"normalized":
|
969 |
"rstrip": false,
|
970 |
"single_word": false,
|
971 |
-
"special":
|
972 |
},
|
973 |
"32118": {
|
974 |
"content": "<|padding_token_116|>",
|
975 |
"lstrip": false,
|
976 |
-
"normalized":
|
977 |
"rstrip": false,
|
978 |
"single_word": false,
|
979 |
-
"special":
|
980 |
},
|
981 |
"32119": {
|
982 |
"content": "<|padding_token_117|>",
|
983 |
"lstrip": false,
|
984 |
-
"normalized":
|
985 |
"rstrip": false,
|
986 |
"single_word": false,
|
987 |
-
"special":
|
988 |
},
|
989 |
"32120": {
|
990 |
"content": "<|padding_token_118|>",
|
991 |
"lstrip": false,
|
992 |
-
"normalized":
|
993 |
"rstrip": false,
|
994 |
"single_word": false,
|
995 |
-
"special":
|
996 |
},
|
997 |
"32121": {
|
998 |
"content": "<|padding_token_119|>",
|
999 |
"lstrip": false,
|
1000 |
-
"normalized":
|
1001 |
"rstrip": false,
|
1002 |
"single_word": false,
|
1003 |
-
"special":
|
1004 |
},
|
1005 |
"32122": {
|
1006 |
"content": "<|padding_token_120|>",
|
1007 |
"lstrip": false,
|
1008 |
-
"normalized":
|
1009 |
"rstrip": false,
|
1010 |
"single_word": false,
|
1011 |
-
"special":
|
1012 |
},
|
1013 |
"32123": {
|
1014 |
"content": "<|padding_token_121|>",
|
1015 |
"lstrip": false,
|
1016 |
-
"normalized":
|
1017 |
"rstrip": false,
|
1018 |
"single_word": false,
|
1019 |
-
"special":
|
1020 |
},
|
1021 |
"32124": {
|
1022 |
"content": "<|padding_token_122|>",
|
1023 |
"lstrip": false,
|
1024 |
-
"normalized":
|
1025 |
"rstrip": false,
|
1026 |
"single_word": false,
|
1027 |
-
"special":
|
1028 |
},
|
1029 |
"32125": {
|
1030 |
"content": "<|padding_token_123|>",
|
1031 |
"lstrip": false,
|
1032 |
-
"normalized":
|
1033 |
"rstrip": false,
|
1034 |
"single_word": false,
|
1035 |
-
"special":
|
1036 |
},
|
1037 |
"32126": {
|
1038 |
"content": "<|padding_token_124|>",
|
1039 |
"lstrip": false,
|
1040 |
-
"normalized":
|
1041 |
"rstrip": false,
|
1042 |
"single_word": false,
|
1043 |
-
"special":
|
1044 |
},
|
1045 |
"32127": {
|
1046 |
"content": "<|padding_token_125|>",
|
1047 |
"lstrip": false,
|
1048 |
-
"normalized":
|
1049 |
"rstrip": false,
|
1050 |
"single_word": false,
|
1051 |
-
"special":
|
1052 |
}
|
1053 |
},
|
1054 |
"additional_special_tokens": [
|
1055 |
"<|im_start|>",
|
1056 |
-
"<|im_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1057 |
],
|
1058 |
"bos_token": "<s>",
|
1059 |
"clean_up_tokenization_spaces": false,
|
|
|
45 |
"32002": {
|
46 |
"content": "<|padding_token_0|>",
|
47 |
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
"rstrip": false,
|
50 |
"single_word": false,
|
51 |
+
"special": true
|
52 |
},
|
53 |
"32003": {
|
54 |
"content": "<|padding_token_1|>",
|
55 |
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
"rstrip": false,
|
58 |
"single_word": false,
|
59 |
+
"special": true
|
60 |
},
|
61 |
"32004": {
|
62 |
"content": "<|padding_token_2|>",
|
63 |
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
"rstrip": false,
|
66 |
"single_word": false,
|
67 |
+
"special": true
|
68 |
},
|
69 |
"32005": {
|
70 |
"content": "<|padding_token_3|>",
|
71 |
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
"rstrip": false,
|
74 |
"single_word": false,
|
75 |
+
"special": true
|
76 |
},
|
77 |
"32006": {
|
78 |
"content": "<|padding_token_4|>",
|
79 |
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
"rstrip": false,
|
82 |
"single_word": false,
|
83 |
+
"special": true
|
84 |
},
|
85 |
"32007": {
|
86 |
"content": "<|padding_token_5|>",
|
87 |
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
"rstrip": false,
|
90 |
"single_word": false,
|
91 |
+
"special": true
|
92 |
},
|
93 |
"32008": {
|
94 |
"content": "<|padding_token_6|>",
|
95 |
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
"rstrip": false,
|
98 |
"single_word": false,
|
99 |
+
"special": true
|
100 |
},
|
101 |
"32009": {
|
102 |
"content": "<|padding_token_7|>",
|
103 |
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
"rstrip": false,
|
106 |
"single_word": false,
|
107 |
+
"special": true
|
108 |
},
|
109 |
"32010": {
|
110 |
"content": "<|padding_token_8|>",
|
111 |
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
"rstrip": false,
|
114 |
"single_word": false,
|
115 |
+
"special": true
|
116 |
},
|
117 |
"32011": {
|
118 |
"content": "<|padding_token_9|>",
|
119 |
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
"rstrip": false,
|
122 |
"single_word": false,
|
123 |
+
"special": true
|
124 |
},
|
125 |
"32012": {
|
126 |
"content": "<|padding_token_10|>",
|
127 |
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
"rstrip": false,
|
130 |
"single_word": false,
|
131 |
+
"special": true
|
132 |
},
|
133 |
"32013": {
|
134 |
"content": "<|padding_token_11|>",
|
135 |
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
"rstrip": false,
|
138 |
"single_word": false,
|
139 |
+
"special": true
|
140 |
},
|
141 |
"32014": {
|
142 |
"content": "<|padding_token_12|>",
|
143 |
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
"rstrip": false,
|
146 |
"single_word": false,
|
147 |
+
"special": true
|
148 |
},
|
149 |
"32015": {
|
150 |
"content": "<|padding_token_13|>",
|
151 |
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
"rstrip": false,
|
154 |
"single_word": false,
|
155 |
+
"special": true
|
156 |
},
|
157 |
"32016": {
|
158 |
"content": "<|padding_token_14|>",
|
159 |
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
"rstrip": false,
|
162 |
"single_word": false,
|
163 |
+
"special": true
|
164 |
},
|
165 |
"32017": {
|
166 |
"content": "<|padding_token_15|>",
|
167 |
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
"rstrip": false,
|
170 |
"single_word": false,
|
171 |
+
"special": true
|
172 |
},
|
173 |
"32018": {
|
174 |
"content": "<|padding_token_16|>",
|
175 |
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
"rstrip": false,
|
178 |
"single_word": false,
|
179 |
+
"special": true
|
180 |
},
|
181 |
"32019": {
|
182 |
"content": "<|padding_token_17|>",
|
183 |
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
"rstrip": false,
|
186 |
"single_word": false,
|
187 |
+
"special": true
|
188 |
},
|
189 |
"32020": {
|
190 |
"content": "<|padding_token_18|>",
|
191 |
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
"rstrip": false,
|
194 |
"single_word": false,
|
195 |
+
"special": true
|
196 |
},
|
197 |
"32021": {
|
198 |
"content": "<|padding_token_19|>",
|
199 |
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
"rstrip": false,
|
202 |
"single_word": false,
|
203 |
+
"special": true
|
204 |
},
|
205 |
"32022": {
|
206 |
"content": "<|padding_token_20|>",
|
207 |
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
"rstrip": false,
|
210 |
"single_word": false,
|
211 |
+
"special": true
|
212 |
},
|
213 |
"32023": {
|
214 |
"content": "<|padding_token_21|>",
|
215 |
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
"rstrip": false,
|
218 |
"single_word": false,
|
219 |
+
"special": true
|
220 |
},
|
221 |
"32024": {
|
222 |
"content": "<|padding_token_22|>",
|
223 |
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
"rstrip": false,
|
226 |
"single_word": false,
|
227 |
+
"special": true
|
228 |
},
|
229 |
"32025": {
|
230 |
"content": "<|padding_token_23|>",
|
231 |
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
"rstrip": false,
|
234 |
"single_word": false,
|
235 |
+
"special": true
|
236 |
},
|
237 |
"32026": {
|
238 |
"content": "<|padding_token_24|>",
|
239 |
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
"rstrip": false,
|
242 |
"single_word": false,
|
243 |
+
"special": true
|
244 |
},
|
245 |
"32027": {
|
246 |
"content": "<|padding_token_25|>",
|
247 |
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
"rstrip": false,
|
250 |
"single_word": false,
|
251 |
+
"special": true
|
252 |
},
|
253 |
"32028": {
|
254 |
"content": "<|padding_token_26|>",
|
255 |
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
"rstrip": false,
|
258 |
"single_word": false,
|
259 |
+
"special": true
|
260 |
},
|
261 |
"32029": {
|
262 |
"content": "<|padding_token_27|>",
|
263 |
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
"rstrip": false,
|
266 |
"single_word": false,
|
267 |
+
"special": true
|
268 |
},
|
269 |
"32030": {
|
270 |
"content": "<|padding_token_28|>",
|
271 |
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
"rstrip": false,
|
274 |
"single_word": false,
|
275 |
+
"special": true
|
276 |
},
|
277 |
"32031": {
|
278 |
"content": "<|padding_token_29|>",
|
279 |
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
"rstrip": false,
|
282 |
"single_word": false,
|
283 |
+
"special": true
|
284 |
},
|
285 |
"32032": {
|
286 |
"content": "<|padding_token_30|>",
|
287 |
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
"rstrip": false,
|
290 |
"single_word": false,
|
291 |
+
"special": true
|
292 |
},
|
293 |
"32033": {
|
294 |
"content": "<|padding_token_31|>",
|
295 |
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
"rstrip": false,
|
298 |
"single_word": false,
|
299 |
+
"special": true
|
300 |
},
|
301 |
"32034": {
|
302 |
"content": "<|padding_token_32|>",
|
303 |
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
"rstrip": false,
|
306 |
"single_word": false,
|
307 |
+
"special": true
|
308 |
},
|
309 |
"32035": {
|
310 |
"content": "<|padding_token_33|>",
|
311 |
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
"rstrip": false,
|
314 |
"single_word": false,
|
315 |
+
"special": true
|
316 |
},
|
317 |
"32036": {
|
318 |
"content": "<|padding_token_34|>",
|
319 |
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
"rstrip": false,
|
322 |
"single_word": false,
|
323 |
+
"special": true
|
324 |
},
|
325 |
"32037": {
|
326 |
"content": "<|padding_token_35|>",
|
327 |
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
"rstrip": false,
|
330 |
"single_word": false,
|
331 |
+
"special": true
|
332 |
},
|
333 |
"32038": {
|
334 |
"content": "<|padding_token_36|>",
|
335 |
"lstrip": false,
|
336 |
+
"normalized": false,
|
337 |
"rstrip": false,
|
338 |
"single_word": false,
|
339 |
+
"special": true
|
340 |
},
|
341 |
"32039": {
|
342 |
"content": "<|padding_token_37|>",
|
343 |
"lstrip": false,
|
344 |
+
"normalized": false,
|
345 |
"rstrip": false,
|
346 |
"single_word": false,
|
347 |
+
"special": true
|
348 |
},
|
349 |
"32040": {
|
350 |
"content": "<|padding_token_38|>",
|
351 |
"lstrip": false,
|
352 |
+
"normalized": false,
|
353 |
"rstrip": false,
|
354 |
"single_word": false,
|
355 |
+
"special": true
|
356 |
},
|
357 |
"32041": {
|
358 |
"content": "<|padding_token_39|>",
|
359 |
"lstrip": false,
|
360 |
+
"normalized": false,
|
361 |
"rstrip": false,
|
362 |
"single_word": false,
|
363 |
+
"special": true
|
364 |
},
|
365 |
"32042": {
|
366 |
"content": "<|padding_token_40|>",
|
367 |
"lstrip": false,
|
368 |
+
"normalized": false,
|
369 |
"rstrip": false,
|
370 |
"single_word": false,
|
371 |
+
"special": true
|
372 |
},
|
373 |
"32043": {
|
374 |
"content": "<|padding_token_41|>",
|
375 |
"lstrip": false,
|
376 |
+
"normalized": false,
|
377 |
"rstrip": false,
|
378 |
"single_word": false,
|
379 |
+
"special": true
|
380 |
},
|
381 |
"32044": {
|
382 |
"content": "<|padding_token_42|>",
|
383 |
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
"rstrip": false,
|
386 |
"single_word": false,
|
387 |
+
"special": true
|
388 |
},
|
389 |
"32045": {
|
390 |
"content": "<|padding_token_43|>",
|
391 |
"lstrip": false,
|
392 |
+
"normalized": false,
|
393 |
"rstrip": false,
|
394 |
"single_word": false,
|
395 |
+
"special": true
|
396 |
},
|
397 |
"32046": {
|
398 |
"content": "<|padding_token_44|>",
|
399 |
"lstrip": false,
|
400 |
+
"normalized": false,
|
401 |
"rstrip": false,
|
402 |
"single_word": false,
|
403 |
+
"special": true
|
404 |
},
|
405 |
"32047": {
|
406 |
"content": "<|padding_token_45|>",
|
407 |
"lstrip": false,
|
408 |
+
"normalized": false,
|
409 |
"rstrip": false,
|
410 |
"single_word": false,
|
411 |
+
"special": true
|
412 |
},
|
413 |
"32048": {
|
414 |
"content": "<|padding_token_46|>",
|
415 |
"lstrip": false,
|
416 |
+
"normalized": false,
|
417 |
"rstrip": false,
|
418 |
"single_word": false,
|
419 |
+
"special": true
|
420 |
},
|
421 |
"32049": {
|
422 |
"content": "<|padding_token_47|>",
|
423 |
"lstrip": false,
|
424 |
+
"normalized": false,
|
425 |
"rstrip": false,
|
426 |
"single_word": false,
|
427 |
+
"special": true
|
428 |
},
|
429 |
"32050": {
|
430 |
"content": "<|padding_token_48|>",
|
431 |
"lstrip": false,
|
432 |
+
"normalized": false,
|
433 |
"rstrip": false,
|
434 |
"single_word": false,
|
435 |
+
"special": true
|
436 |
},
|
437 |
"32051": {
|
438 |
"content": "<|padding_token_49|>",
|
439 |
"lstrip": false,
|
440 |
+
"normalized": false,
|
441 |
"rstrip": false,
|
442 |
"single_word": false,
|
443 |
+
"special": true
|
444 |
},
|
445 |
"32052": {
|
446 |
"content": "<|padding_token_50|>",
|
447 |
"lstrip": false,
|
448 |
+
"normalized": false,
|
449 |
"rstrip": false,
|
450 |
"single_word": false,
|
451 |
+
"special": true
|
452 |
},
|
453 |
"32053": {
|
454 |
"content": "<|padding_token_51|>",
|
455 |
"lstrip": false,
|
456 |
+
"normalized": false,
|
457 |
"rstrip": false,
|
458 |
"single_word": false,
|
459 |
+
"special": true
|
460 |
},
|
461 |
"32054": {
|
462 |
"content": "<|padding_token_52|>",
|
463 |
"lstrip": false,
|
464 |
+
"normalized": false,
|
465 |
"rstrip": false,
|
466 |
"single_word": false,
|
467 |
+
"special": true
|
468 |
},
|
469 |
"32055": {
|
470 |
"content": "<|padding_token_53|>",
|
471 |
"lstrip": false,
|
472 |
+
"normalized": false,
|
473 |
"rstrip": false,
|
474 |
"single_word": false,
|
475 |
+
"special": true
|
476 |
},
|
477 |
"32056": {
|
478 |
"content": "<|padding_token_54|>",
|
479 |
"lstrip": false,
|
480 |
+
"normalized": false,
|
481 |
"rstrip": false,
|
482 |
"single_word": false,
|
483 |
+
"special": true
|
484 |
},
|
485 |
"32057": {
|
486 |
"content": "<|padding_token_55|>",
|
487 |
"lstrip": false,
|
488 |
+
"normalized": false,
|
489 |
"rstrip": false,
|
490 |
"single_word": false,
|
491 |
+
"special": true
|
492 |
},
|
493 |
"32058": {
|
494 |
"content": "<|padding_token_56|>",
|
495 |
"lstrip": false,
|
496 |
+
"normalized": false,
|
497 |
"rstrip": false,
|
498 |
"single_word": false,
|
499 |
+
"special": true
|
500 |
},
|
501 |
"32059": {
|
502 |
"content": "<|padding_token_57|>",
|
503 |
"lstrip": false,
|
504 |
+
"normalized": false,
|
505 |
"rstrip": false,
|
506 |
"single_word": false,
|
507 |
+
"special": true
|
508 |
},
|
509 |
"32060": {
|
510 |
"content": "<|padding_token_58|>",
|
511 |
"lstrip": false,
|
512 |
+
"normalized": false,
|
513 |
"rstrip": false,
|
514 |
"single_word": false,
|
515 |
+
"special": true
|
516 |
},
|
517 |
"32061": {
|
518 |
"content": "<|padding_token_59|>",
|
519 |
"lstrip": false,
|
520 |
+
"normalized": false,
|
521 |
"rstrip": false,
|
522 |
"single_word": false,
|
523 |
+
"special": true
|
524 |
},
|
525 |
"32062": {
|
526 |
"content": "<|padding_token_60|>",
|
527 |
"lstrip": false,
|
528 |
+
"normalized": false,
|
529 |
"rstrip": false,
|
530 |
"single_word": false,
|
531 |
+
"special": true
|
532 |
},
|
533 |
"32063": {
|
534 |
"content": "<|padding_token_61|>",
|
535 |
"lstrip": false,
|
536 |
+
"normalized": false,
|
537 |
"rstrip": false,
|
538 |
"single_word": false,
|
539 |
+
"special": true
|
540 |
},
|
541 |
"32064": {
|
542 |
"content": "<|padding_token_62|>",
|
543 |
"lstrip": false,
|
544 |
+
"normalized": false,
|
545 |
"rstrip": false,
|
546 |
"single_word": false,
|
547 |
+
"special": true
|
548 |
},
|
549 |
"32065": {
|
550 |
"content": "<|padding_token_63|>",
|
551 |
"lstrip": false,
|
552 |
+
"normalized": false,
|
553 |
"rstrip": false,
|
554 |
"single_word": false,
|
555 |
+
"special": true
|
556 |
},
|
557 |
"32066": {
|
558 |
"content": "<|padding_token_64|>",
|
559 |
"lstrip": false,
|
560 |
+
"normalized": false,
|
561 |
"rstrip": false,
|
562 |
"single_word": false,
|
563 |
+
"special": true
|
564 |
},
|
565 |
"32067": {
|
566 |
"content": "<|padding_token_65|>",
|
567 |
"lstrip": false,
|
568 |
+
"normalized": false,
|
569 |
"rstrip": false,
|
570 |
"single_word": false,
|
571 |
+
"special": true
|
572 |
},
|
573 |
"32068": {
|
574 |
"content": "<|padding_token_66|>",
|
575 |
"lstrip": false,
|
576 |
+
"normalized": false,
|
577 |
"rstrip": false,
|
578 |
"single_word": false,
|
579 |
+
"special": true
|
580 |
},
|
581 |
"32069": {
|
582 |
"content": "<|padding_token_67|>",
|
583 |
"lstrip": false,
|
584 |
+
"normalized": false,
|
585 |
"rstrip": false,
|
586 |
"single_word": false,
|
587 |
+
"special": true
|
588 |
},
|
589 |
"32070": {
|
590 |
"content": "<|padding_token_68|>",
|
591 |
"lstrip": false,
|
592 |
+
"normalized": false,
|
593 |
"rstrip": false,
|
594 |
"single_word": false,
|
595 |
+
"special": true
|
596 |
},
|
597 |
"32071": {
|
598 |
"content": "<|padding_token_69|>",
|
599 |
"lstrip": false,
|
600 |
+
"normalized": false,
|
601 |
"rstrip": false,
|
602 |
"single_word": false,
|
603 |
+
"special": true
|
604 |
},
|
605 |
"32072": {
|
606 |
"content": "<|padding_token_70|>",
|
607 |
"lstrip": false,
|
608 |
+
"normalized": false,
|
609 |
"rstrip": false,
|
610 |
"single_word": false,
|
611 |
+
"special": true
|
612 |
},
|
613 |
"32073": {
|
614 |
"content": "<|padding_token_71|>",
|
615 |
"lstrip": false,
|
616 |
+
"normalized": false,
|
617 |
"rstrip": false,
|
618 |
"single_word": false,
|
619 |
+
"special": true
|
620 |
},
|
621 |
"32074": {
|
622 |
"content": "<|padding_token_72|>",
|
623 |
"lstrip": false,
|
624 |
+
"normalized": false,
|
625 |
"rstrip": false,
|
626 |
"single_word": false,
|
627 |
+
"special": true
|
628 |
},
|
629 |
"32075": {
|
630 |
"content": "<|padding_token_73|>",
|
631 |
"lstrip": false,
|
632 |
+
"normalized": false,
|
633 |
"rstrip": false,
|
634 |
"single_word": false,
|
635 |
+
"special": true
|
636 |
},
|
637 |
"32076": {
|
638 |
"content": "<|padding_token_74|>",
|
639 |
"lstrip": false,
|
640 |
+
"normalized": false,
|
641 |
"rstrip": false,
|
642 |
"single_word": false,
|
643 |
+
"special": true
|
644 |
},
|
645 |
"32077": {
|
646 |
"content": "<|padding_token_75|>",
|
647 |
"lstrip": false,
|
648 |
+
"normalized": false,
|
649 |
"rstrip": false,
|
650 |
"single_word": false,
|
651 |
+
"special": true
|
652 |
},
|
653 |
"32078": {
|
654 |
"content": "<|padding_token_76|>",
|
655 |
"lstrip": false,
|
656 |
+
"normalized": false,
|
657 |
"rstrip": false,
|
658 |
"single_word": false,
|
659 |
+
"special": true
|
660 |
},
|
661 |
"32079": {
|
662 |
"content": "<|padding_token_77|>",
|
663 |
"lstrip": false,
|
664 |
+
"normalized": false,
|
665 |
"rstrip": false,
|
666 |
"single_word": false,
|
667 |
+
"special": true
|
668 |
},
|
669 |
"32080": {
|
670 |
"content": "<|padding_token_78|>",
|
671 |
"lstrip": false,
|
672 |
+
"normalized": false,
|
673 |
"rstrip": false,
|
674 |
"single_word": false,
|
675 |
+
"special": true
|
676 |
},
|
677 |
"32081": {
|
678 |
"content": "<|padding_token_79|>",
|
679 |
"lstrip": false,
|
680 |
+
"normalized": false,
|
681 |
"rstrip": false,
|
682 |
"single_word": false,
|
683 |
+
"special": true
|
684 |
},
|
685 |
"32082": {
|
686 |
"content": "<|padding_token_80|>",
|
687 |
"lstrip": false,
|
688 |
+
"normalized": false,
|
689 |
"rstrip": false,
|
690 |
"single_word": false,
|
691 |
+
"special": true
|
692 |
},
|
693 |
"32083": {
|
694 |
"content": "<|padding_token_81|>",
|
695 |
"lstrip": false,
|
696 |
+
"normalized": false,
|
697 |
"rstrip": false,
|
698 |
"single_word": false,
|
699 |
+
"special": true
|
700 |
},
|
701 |
"32084": {
|
702 |
"content": "<|padding_token_82|>",
|
703 |
"lstrip": false,
|
704 |
+
"normalized": false,
|
705 |
"rstrip": false,
|
706 |
"single_word": false,
|
707 |
+
"special": true
|
708 |
},
|
709 |
"32085": {
|
710 |
"content": "<|padding_token_83|>",
|
711 |
"lstrip": false,
|
712 |
+
"normalized": false,
|
713 |
"rstrip": false,
|
714 |
"single_word": false,
|
715 |
+
"special": true
|
716 |
},
|
717 |
"32086": {
|
718 |
"content": "<|padding_token_84|>",
|
719 |
"lstrip": false,
|
720 |
+
"normalized": false,
|
721 |
"rstrip": false,
|
722 |
"single_word": false,
|
723 |
+
"special": true
|
724 |
},
|
725 |
"32087": {
|
726 |
"content": "<|padding_token_85|>",
|
727 |
"lstrip": false,
|
728 |
+
"normalized": false,
|
729 |
"rstrip": false,
|
730 |
"single_word": false,
|
731 |
+
"special": true
|
732 |
},
|
733 |
"32088": {
|
734 |
"content": "<|padding_token_86|>",
|
735 |
"lstrip": false,
|
736 |
+
"normalized": false,
|
737 |
"rstrip": false,
|
738 |
"single_word": false,
|
739 |
+
"special": true
|
740 |
},
|
741 |
"32089": {
|
742 |
"content": "<|padding_token_87|>",
|
743 |
"lstrip": false,
|
744 |
+
"normalized": false,
|
745 |
"rstrip": false,
|
746 |
"single_word": false,
|
747 |
+
"special": true
|
748 |
},
|
749 |
"32090": {
|
750 |
"content": "<|padding_token_88|>",
|
751 |
"lstrip": false,
|
752 |
+
"normalized": false,
|
753 |
"rstrip": false,
|
754 |
"single_word": false,
|
755 |
+
"special": true
|
756 |
},
|
757 |
"32091": {
|
758 |
"content": "<|padding_token_89|>",
|
759 |
"lstrip": false,
|
760 |
+
"normalized": false,
|
761 |
"rstrip": false,
|
762 |
"single_word": false,
|
763 |
+
"special": true
|
764 |
},
|
765 |
"32092": {
|
766 |
"content": "<|padding_token_90|>",
|
767 |
"lstrip": false,
|
768 |
+
"normalized": false,
|
769 |
"rstrip": false,
|
770 |
"single_word": false,
|
771 |
+
"special": true
|
772 |
},
|
773 |
"32093": {
|
774 |
"content": "<|padding_token_91|>",
|
775 |
"lstrip": false,
|
776 |
+
"normalized": false,
|
777 |
"rstrip": false,
|
778 |
"single_word": false,
|
779 |
+
"special": true
|
780 |
},
|
781 |
"32094": {
|
782 |
"content": "<|padding_token_92|>",
|
783 |
"lstrip": false,
|
784 |
+
"normalized": false,
|
785 |
"rstrip": false,
|
786 |
"single_word": false,
|
787 |
+
"special": true
|
788 |
},
|
789 |
"32095": {
|
790 |
"content": "<|padding_token_93|>",
|
791 |
"lstrip": false,
|
792 |
+
"normalized": false,
|
793 |
"rstrip": false,
|
794 |
"single_word": false,
|
795 |
+
"special": true
|
796 |
},
|
797 |
"32096": {
|
798 |
"content": "<|padding_token_94|>",
|
799 |
"lstrip": false,
|
800 |
+
"normalized": false,
|
801 |
"rstrip": false,
|
802 |
"single_word": false,
|
803 |
+
"special": true
|
804 |
},
|
805 |
"32097": {
|
806 |
"content": "<|padding_token_95|>",
|
807 |
"lstrip": false,
|
808 |
+
"normalized": false,
|
809 |
"rstrip": false,
|
810 |
"single_word": false,
|
811 |
+
"special": true
|
812 |
},
|
813 |
"32098": {
|
814 |
"content": "<|padding_token_96|>",
|
815 |
"lstrip": false,
|
816 |
+
"normalized": false,
|
817 |
"rstrip": false,
|
818 |
"single_word": false,
|
819 |
+
"special": true
|
820 |
},
|
821 |
"32099": {
|
822 |
"content": "<|padding_token_97|>",
|
823 |
"lstrip": false,
|
824 |
+
"normalized": false,
|
825 |
"rstrip": false,
|
826 |
"single_word": false,
|
827 |
+
"special": true
|
828 |
},
|
829 |
"32100": {
|
830 |
"content": "<|padding_token_98|>",
|
831 |
"lstrip": false,
|
832 |
+
"normalized": false,
|
833 |
"rstrip": false,
|
834 |
"single_word": false,
|
835 |
+
"special": true
|
836 |
},
|
837 |
"32101": {
|
838 |
"content": "<|padding_token_99|>",
|
839 |
"lstrip": false,
|
840 |
+
"normalized": false,
|
841 |
"rstrip": false,
|
842 |
"single_word": false,
|
843 |
+
"special": true
|
844 |
},
|
845 |
"32102": {
|
846 |
"content": "<|padding_token_100|>",
|
847 |
"lstrip": false,
|
848 |
+
"normalized": false,
|
849 |
"rstrip": false,
|
850 |
"single_word": false,
|
851 |
+
"special": true
|
852 |
},
|
853 |
"32103": {
|
854 |
"content": "<|padding_token_101|>",
|
855 |
"lstrip": false,
|
856 |
+
"normalized": false,
|
857 |
"rstrip": false,
|
858 |
"single_word": false,
|
859 |
+
"special": true
|
860 |
},
|
861 |
"32104": {
|
862 |
"content": "<|padding_token_102|>",
|
863 |
"lstrip": false,
|
864 |
+
"normalized": false,
|
865 |
"rstrip": false,
|
866 |
"single_word": false,
|
867 |
+
"special": true
|
868 |
},
|
869 |
"32105": {
|
870 |
"content": "<|padding_token_103|>",
|
871 |
"lstrip": false,
|
872 |
+
"normalized": false,
|
873 |
"rstrip": false,
|
874 |
"single_word": false,
|
875 |
+
"special": true
|
876 |
},
|
877 |
"32106": {
|
878 |
"content": "<|padding_token_104|>",
|
879 |
"lstrip": false,
|
880 |
+
"normalized": false,
|
881 |
"rstrip": false,
|
882 |
"single_word": false,
|
883 |
+
"special": true
|
884 |
},
|
885 |
"32107": {
|
886 |
"content": "<|padding_token_105|>",
|
887 |
"lstrip": false,
|
888 |
+
"normalized": false,
|
889 |
"rstrip": false,
|
890 |
"single_word": false,
|
891 |
+
"special": true
|
892 |
},
|
893 |
"32108": {
|
894 |
"content": "<|padding_token_106|>",
|
895 |
"lstrip": false,
|
896 |
+
"normalized": false,
|
897 |
"rstrip": false,
|
898 |
"single_word": false,
|
899 |
+
"special": true
|
900 |
},
|
901 |
"32109": {
|
902 |
"content": "<|padding_token_107|>",
|
903 |
"lstrip": false,
|
904 |
+
"normalized": false,
|
905 |
"rstrip": false,
|
906 |
"single_word": false,
|
907 |
+
"special": true
|
908 |
},
|
909 |
"32110": {
|
910 |
"content": "<|padding_token_108|>",
|
911 |
"lstrip": false,
|
912 |
+
"normalized": false,
|
913 |
"rstrip": false,
|
914 |
"single_word": false,
|
915 |
+
"special": true
|
916 |
},
|
917 |
"32111": {
|
918 |
"content": "<|padding_token_109|>",
|
919 |
"lstrip": false,
|
920 |
+
"normalized": false,
|
921 |
"rstrip": false,
|
922 |
"single_word": false,
|
923 |
+
"special": true
|
924 |
},
|
925 |
"32112": {
|
926 |
"content": "<|padding_token_110|>",
|
927 |
"lstrip": false,
|
928 |
+
"normalized": false,
|
929 |
"rstrip": false,
|
930 |
"single_word": false,
|
931 |
+
"special": true
|
932 |
},
|
933 |
"32113": {
|
934 |
"content": "<|padding_token_111|>",
|
935 |
"lstrip": false,
|
936 |
+
"normalized": false,
|
937 |
"rstrip": false,
|
938 |
"single_word": false,
|
939 |
+
"special": true
|
940 |
},
|
941 |
"32114": {
|
942 |
"content": "<|padding_token_112|>",
|
943 |
"lstrip": false,
|
944 |
+
"normalized": false,
|
945 |
"rstrip": false,
|
946 |
"single_word": false,
|
947 |
+
"special": true
|
948 |
},
|
949 |
"32115": {
|
950 |
"content": "<|padding_token_113|>",
|
951 |
"lstrip": false,
|
952 |
+
"normalized": false,
|
953 |
"rstrip": false,
|
954 |
"single_word": false,
|
955 |
+
"special": true
|
956 |
},
|
957 |
"32116": {
|
958 |
"content": "<|padding_token_114|>",
|
959 |
"lstrip": false,
|
960 |
+
"normalized": false,
|
961 |
"rstrip": false,
|
962 |
"single_word": false,
|
963 |
+
"special": true
|
964 |
},
|
965 |
"32117": {
|
966 |
"content": "<|padding_token_115|>",
|
967 |
"lstrip": false,
|
968 |
+
"normalized": false,
|
969 |
"rstrip": false,
|
970 |
"single_word": false,
|
971 |
+
"special": true
|
972 |
},
|
973 |
"32118": {
|
974 |
"content": "<|padding_token_116|>",
|
975 |
"lstrip": false,
|
976 |
+
"normalized": false,
|
977 |
"rstrip": false,
|
978 |
"single_word": false,
|
979 |
+
"special": true
|
980 |
},
|
981 |
"32119": {
|
982 |
"content": "<|padding_token_117|>",
|
983 |
"lstrip": false,
|
984 |
+
"normalized": false,
|
985 |
"rstrip": false,
|
986 |
"single_word": false,
|
987 |
+
"special": true
|
988 |
},
|
989 |
"32120": {
|
990 |
"content": "<|padding_token_118|>",
|
991 |
"lstrip": false,
|
992 |
+
"normalized": false,
|
993 |
"rstrip": false,
|
994 |
"single_word": false,
|
995 |
+
"special": true
|
996 |
},
|
997 |
"32121": {
|
998 |
"content": "<|padding_token_119|>",
|
999 |
"lstrip": false,
|
1000 |
+
"normalized": false,
|
1001 |
"rstrip": false,
|
1002 |
"single_word": false,
|
1003 |
+
"special": true
|
1004 |
},
|
1005 |
"32122": {
|
1006 |
"content": "<|padding_token_120|>",
|
1007 |
"lstrip": false,
|
1008 |
+
"normalized": false,
|
1009 |
"rstrip": false,
|
1010 |
"single_word": false,
|
1011 |
+
"special": true
|
1012 |
},
|
1013 |
"32123": {
|
1014 |
"content": "<|padding_token_121|>",
|
1015 |
"lstrip": false,
|
1016 |
+
"normalized": false,
|
1017 |
"rstrip": false,
|
1018 |
"single_word": false,
|
1019 |
+
"special": true
|
1020 |
},
|
1021 |
"32124": {
|
1022 |
"content": "<|padding_token_122|>",
|
1023 |
"lstrip": false,
|
1024 |
+
"normalized": false,
|
1025 |
"rstrip": false,
|
1026 |
"single_word": false,
|
1027 |
+
"special": true
|
1028 |
},
|
1029 |
"32125": {
|
1030 |
"content": "<|padding_token_123|>",
|
1031 |
"lstrip": false,
|
1032 |
+
"normalized": false,
|
1033 |
"rstrip": false,
|
1034 |
"single_word": false,
|
1035 |
+
"special": true
|
1036 |
},
|
1037 |
"32126": {
|
1038 |
"content": "<|padding_token_124|>",
|
1039 |
"lstrip": false,
|
1040 |
+
"normalized": false,
|
1041 |
"rstrip": false,
|
1042 |
"single_word": false,
|
1043 |
+
"special": true
|
1044 |
},
|
1045 |
"32127": {
|
1046 |
"content": "<|padding_token_125|>",
|
1047 |
"lstrip": false,
|
1048 |
+
"normalized": false,
|
1049 |
"rstrip": false,
|
1050 |
"single_word": false,
|
1051 |
+
"special": true
|
1052 |
}
|
1053 |
},
|
1054 |
"additional_special_tokens": [
|
1055 |
"<|im_start|>",
|
1056 |
+
"<|im_end|>",
|
1057 |
+
"<|padding_token_0|>",
|
1058 |
+
"<|padding_token_1|>",
|
1059 |
+
"<|padding_token_2|>",
|
1060 |
+
"<|padding_token_3|>",
|
1061 |
+
"<|padding_token_4|>",
|
1062 |
+
"<|padding_token_5|>",
|
1063 |
+
"<|padding_token_6|>",
|
1064 |
+
"<|padding_token_7|>",
|
1065 |
+
"<|padding_token_8|>",
|
1066 |
+
"<|padding_token_9|>",
|
1067 |
+
"<|padding_token_10|>",
|
1068 |
+
"<|padding_token_11|>",
|
1069 |
+
"<|padding_token_12|>",
|
1070 |
+
"<|padding_token_13|>",
|
1071 |
+
"<|padding_token_14|>",
|
1072 |
+
"<|padding_token_15|>",
|
1073 |
+
"<|padding_token_16|>",
|
1074 |
+
"<|padding_token_17|>",
|
1075 |
+
"<|padding_token_18|>",
|
1076 |
+
"<|padding_token_19|>",
|
1077 |
+
"<|padding_token_20|>",
|
1078 |
+
"<|padding_token_21|>",
|
1079 |
+
"<|padding_token_22|>",
|
1080 |
+
"<|padding_token_23|>",
|
1081 |
+
"<|padding_token_24|>",
|
1082 |
+
"<|padding_token_25|>",
|
1083 |
+
"<|padding_token_26|>",
|
1084 |
+
"<|padding_token_27|>",
|
1085 |
+
"<|padding_token_28|>",
|
1086 |
+
"<|padding_token_29|>",
|
1087 |
+
"<|padding_token_30|>",
|
1088 |
+
"<|padding_token_31|>",
|
1089 |
+
"<|padding_token_32|>",
|
1090 |
+
"<|padding_token_33|>",
|
1091 |
+
"<|padding_token_34|>",
|
1092 |
+
"<|padding_token_35|>",
|
1093 |
+
"<|padding_token_36|>",
|
1094 |
+
"<|padding_token_37|>",
|
1095 |
+
"<|padding_token_38|>",
|
1096 |
+
"<|padding_token_39|>",
|
1097 |
+
"<|padding_token_40|>",
|
1098 |
+
"<|padding_token_41|>",
|
1099 |
+
"<|padding_token_42|>",
|
1100 |
+
"<|padding_token_43|>",
|
1101 |
+
"<|padding_token_44|>",
|
1102 |
+
"<|padding_token_45|>",
|
1103 |
+
"<|padding_token_46|>",
|
1104 |
+
"<|padding_token_47|>",
|
1105 |
+
"<|padding_token_48|>",
|
1106 |
+
"<|padding_token_49|>",
|
1107 |
+
"<|padding_token_50|>",
|
1108 |
+
"<|padding_token_51|>",
|
1109 |
+
"<|padding_token_52|>",
|
1110 |
+
"<|padding_token_53|>",
|
1111 |
+
"<|padding_token_54|>",
|
1112 |
+
"<|padding_token_55|>",
|
1113 |
+
"<|padding_token_56|>",
|
1114 |
+
"<|padding_token_57|>",
|
1115 |
+
"<|padding_token_58|>",
|
1116 |
+
"<|padding_token_59|>",
|
1117 |
+
"<|padding_token_60|>",
|
1118 |
+
"<|padding_token_61|>",
|
1119 |
+
"<|padding_token_62|>",
|
1120 |
+
"<|padding_token_63|>",
|
1121 |
+
"<|padding_token_64|>",
|
1122 |
+
"<|padding_token_65|>",
|
1123 |
+
"<|padding_token_66|>",
|
1124 |
+
"<|padding_token_67|>",
|
1125 |
+
"<|padding_token_68|>",
|
1126 |
+
"<|padding_token_69|>",
|
1127 |
+
"<|padding_token_70|>",
|
1128 |
+
"<|padding_token_71|>",
|
1129 |
+
"<|padding_token_72|>",
|
1130 |
+
"<|padding_token_73|>",
|
1131 |
+
"<|padding_token_74|>",
|
1132 |
+
"<|padding_token_75|>",
|
1133 |
+
"<|padding_token_76|>",
|
1134 |
+
"<|padding_token_77|>",
|
1135 |
+
"<|padding_token_78|>",
|
1136 |
+
"<|padding_token_79|>",
|
1137 |
+
"<|padding_token_80|>",
|
1138 |
+
"<|padding_token_81|>",
|
1139 |
+
"<|padding_token_82|>",
|
1140 |
+
"<|padding_token_83|>",
|
1141 |
+
"<|padding_token_84|>",
|
1142 |
+
"<|padding_token_85|>",
|
1143 |
+
"<|padding_token_86|>",
|
1144 |
+
"<|padding_token_87|>",
|
1145 |
+
"<|padding_token_88|>",
|
1146 |
+
"<|padding_token_89|>",
|
1147 |
+
"<|padding_token_90|>",
|
1148 |
+
"<|padding_token_91|>",
|
1149 |
+
"<|padding_token_92|>",
|
1150 |
+
"<|padding_token_93|>",
|
1151 |
+
"<|padding_token_94|>",
|
1152 |
+
"<|padding_token_95|>",
|
1153 |
+
"<|padding_token_96|>",
|
1154 |
+
"<|padding_token_97|>",
|
1155 |
+
"<|padding_token_98|>",
|
1156 |
+
"<|padding_token_99|>",
|
1157 |
+
"<|padding_token_100|>",
|
1158 |
+
"<|padding_token_101|>",
|
1159 |
+
"<|padding_token_102|>",
|
1160 |
+
"<|padding_token_103|>",
|
1161 |
+
"<|padding_token_104|>",
|
1162 |
+
"<|padding_token_105|>",
|
1163 |
+
"<|padding_token_106|>",
|
1164 |
+
"<|padding_token_107|>",
|
1165 |
+
"<|padding_token_108|>",
|
1166 |
+
"<|padding_token_109|>",
|
1167 |
+
"<|padding_token_110|>",
|
1168 |
+
"<|padding_token_111|>",
|
1169 |
+
"<|padding_token_112|>",
|
1170 |
+
"<|padding_token_113|>",
|
1171 |
+
"<|padding_token_114|>",
|
1172 |
+
"<|padding_token_115|>",
|
1173 |
+
"<|padding_token_116|>",
|
1174 |
+
"<|padding_token_117|>",
|
1175 |
+
"<|padding_token_118|>",
|
1176 |
+
"<|padding_token_119|>",
|
1177 |
+
"<|padding_token_120|>",
|
1178 |
+
"<|padding_token_121|>",
|
1179 |
+
"<|padding_token_122|>",
|
1180 |
+
"<|padding_token_123|>",
|
1181 |
+
"<|padding_token_124|>",
|
1182 |
+
"<|padding_token_125|>"
|
1183 |
],
|
1184 |
"bos_token": "<s>",
|
1185 |
"clean_up_tokenization_spaces": false,
|