yuntaeyang
commited on
Commit
•
715d4f9
1
Parent(s):
81fea08
Upload tokenizer
Browse files- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +453 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,453 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"78413": {
|
30 |
+
"content": "<|sep|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"78414": {
|
38 |
+
"content": "<|acc|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"78415": {
|
46 |
+
"content": "<|rrn|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"78416": {
|
54 |
+
"content": "<|tel|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"78417": {
|
62 |
+
"content": "ㄱ",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"78418": {
|
70 |
+
"content": "ㄴ",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"78419": {
|
78 |
+
"content": "ㄷ",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"78420": {
|
86 |
+
"content": "ㄹ",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"78421": {
|
94 |
+
"content": "ㅁ",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"78422": {
|
102 |
+
"content": "ㅂ",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"78423": {
|
110 |
+
"content": "ㅅ",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"78424": {
|
118 |
+
"content": "ㅇ",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"78425": {
|
126 |
+
"content": "ㅈ",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"78426": {
|
134 |
+
"content": "ㅊ",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"78427": {
|
142 |
+
"content": "ㅋ",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"78428": {
|
150 |
+
"content": "ㅌ",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"78429": {
|
158 |
+
"content": "ㅍ",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"78430": {
|
166 |
+
"content": "ㅎ",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"78431": {
|
174 |
+
"content": "ㅏ",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"78432": {
|
182 |
+
"content": "ㅐ",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": true
|
188 |
+
},
|
189 |
+
"78433": {
|
190 |
+
"content": "ㅑ",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": true
|
196 |
+
},
|
197 |
+
"78434": {
|
198 |
+
"content": "ㅒ",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": true
|
204 |
+
},
|
205 |
+
"78435": {
|
206 |
+
"content": "ㅓ",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
"78436": {
|
214 |
+
"content": "ㅔ",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": true
|
220 |
+
},
|
221 |
+
"78437": {
|
222 |
+
"content": "ㅕ",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": true
|
228 |
+
},
|
229 |
+
"78438": {
|
230 |
+
"content": "ㅖ",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": true
|
236 |
+
},
|
237 |
+
"78439": {
|
238 |
+
"content": "ㅗ",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": true
|
244 |
+
},
|
245 |
+
"78440": {
|
246 |
+
"content": "ㅘ",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": true
|
252 |
+
},
|
253 |
+
"78441": {
|
254 |
+
"content": "ㅙ",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": true
|
260 |
+
},
|
261 |
+
"78442": {
|
262 |
+
"content": "ㅚ",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": true
|
268 |
+
},
|
269 |
+
"78443": {
|
270 |
+
"content": "ㅛ",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": true
|
276 |
+
},
|
277 |
+
"78444": {
|
278 |
+
"content": "ㅜ",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": true
|
284 |
+
},
|
285 |
+
"78445": {
|
286 |
+
"content": "ㅝ",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": true
|
292 |
+
},
|
293 |
+
"78446": {
|
294 |
+
"content": "ㅞ",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": true
|
300 |
+
},
|
301 |
+
"78447": {
|
302 |
+
"content": "ㅟ",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": true
|
308 |
+
},
|
309 |
+
"78448": {
|
310 |
+
"content": "ㅠ",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": true
|
316 |
+
},
|
317 |
+
"78449": {
|
318 |
+
"content": "ㅡ",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": true
|
324 |
+
},
|
325 |
+
"78450": {
|
326 |
+
"content": "ㅢ",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": true
|
332 |
+
},
|
333 |
+
"78451": {
|
334 |
+
"content": "ㅣ",
|
335 |
+
"lstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false,
|
339 |
+
"special": true
|
340 |
+
},
|
341 |
+
"78452": {
|
342 |
+
"content": "ㄲ",
|
343 |
+
"lstrip": false,
|
344 |
+
"normalized": false,
|
345 |
+
"rstrip": false,
|
346 |
+
"single_word": false,
|
347 |
+
"special": true
|
348 |
+
},
|
349 |
+
"78453": {
|
350 |
+
"content": "ㄳ",
|
351 |
+
"lstrip": false,
|
352 |
+
"normalized": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"single_word": false,
|
355 |
+
"special": true
|
356 |
+
},
|
357 |
+
"78454": {
|
358 |
+
"content": "ㄵ",
|
359 |
+
"lstrip": false,
|
360 |
+
"normalized": false,
|
361 |
+
"rstrip": false,
|
362 |
+
"single_word": false,
|
363 |
+
"special": true
|
364 |
+
},
|
365 |
+
"78455": {
|
366 |
+
"content": "ㄶ",
|
367 |
+
"lstrip": false,
|
368 |
+
"normalized": false,
|
369 |
+
"rstrip": false,
|
370 |
+
"single_word": false,
|
371 |
+
"special": true
|
372 |
+
},
|
373 |
+
"78456": {
|
374 |
+
"content": "ㄺ",
|
375 |
+
"lstrip": false,
|
376 |
+
"normalized": false,
|
377 |
+
"rstrip": false,
|
378 |
+
"single_word": false,
|
379 |
+
"special": true
|
380 |
+
},
|
381 |
+
"78457": {
|
382 |
+
"content": "ㄻ",
|
383 |
+
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false,
|
387 |
+
"special": true
|
388 |
+
},
|
389 |
+
"78458": {
|
390 |
+
"content": "ㄼ",
|
391 |
+
"lstrip": false,
|
392 |
+
"normalized": false,
|
393 |
+
"rstrip": false,
|
394 |
+
"single_word": false,
|
395 |
+
"special": true
|
396 |
+
},
|
397 |
+
"78459": {
|
398 |
+
"content": "ㄽ",
|
399 |
+
"lstrip": false,
|
400 |
+
"normalized": false,
|
401 |
+
"rstrip": false,
|
402 |
+
"single_word": false,
|
403 |
+
"special": true
|
404 |
+
},
|
405 |
+
"78460": {
|
406 |
+
"content": "ㄾ",
|
407 |
+
"lstrip": false,
|
408 |
+
"normalized": false,
|
409 |
+
"rstrip": false,
|
410 |
+
"single_word": false,
|
411 |
+
"special": true
|
412 |
+
},
|
413 |
+
"78461": {
|
414 |
+
"content": "ㄿ",
|
415 |
+
"lstrip": false,
|
416 |
+
"normalized": false,
|
417 |
+
"rstrip": false,
|
418 |
+
"single_word": false,
|
419 |
+
"special": true
|
420 |
+
},
|
421 |
+
"78462": {
|
422 |
+
"content": "ㅀ",
|
423 |
+
"lstrip": false,
|
424 |
+
"normalized": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"single_word": false,
|
427 |
+
"special": true
|
428 |
+
},
|
429 |
+
"78463": {
|
430 |
+
"content": "ㅄ",
|
431 |
+
"lstrip": false,
|
432 |
+
"normalized": false,
|
433 |
+
"rstrip": false,
|
434 |
+
"single_word": false,
|
435 |
+
"special": true
|
436 |
+
}
|
437 |
+
},
|
438 |
+
"bos_token": "<|startoftext|>",
|
439 |
+
"clean_up_tokenization_spaces": false,
|
440 |
+
"eos_token": "<|endoftext|>",
|
441 |
+
"fast": true,
|
442 |
+
"legacy": true,
|
443 |
+
"max_length": 4096,
|
444 |
+
"model_max_length": 4096,
|
445 |
+
"pad_token": "<|endoftext|>",
|
446 |
+
"sp_model_kwargs": {},
|
447 |
+
"stride": 0,
|
448 |
+
"tokenizer_class": "LlamaTokenizer",
|
449 |
+
"truncation_side": "right",
|
450 |
+
"truncation_strategy": "longest_first",
|
451 |
+
"unk_token": "<unk>",
|
452 |
+
"use_default_system_prompt": true
|
453 |
+
}
|