Upload tokenizer
Browse files- merges.txt +647 -0
- special_tokens_map.json +6 -0
- tokenizer.json +1740 -0
- tokenizer_config.json +32 -0
- vocab.json +1 -0
merges.txt
ADDED
@@ -0,0 +1,647 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#version: 0.2
|
2 |
+
Ġ t
|
3 |
+
Ġt h
|
4 |
+
Ġ a
|
5 |
+
Ġth e</w>
|
6 |
+
i n
|
7 |
+
Ġ o
|
8 |
+
Ġ ,</w>
|
9 |
+
Ġ s
|
10 |
+
e d</w>
|
11 |
+
Ġ w
|
12 |
+
e r
|
13 |
+
Ġ .</w>
|
14 |
+
Ġ i
|
15 |
+
r e
|
16 |
+
Ġ c
|
17 |
+
n d</w>
|
18 |
+
Ġ f
|
19 |
+
Ġ b
|
20 |
+
a t
|
21 |
+
Ġo f</w>
|
22 |
+
e r</w>
|
23 |
+
e n
|
24 |
+
a r
|
25 |
+
o r
|
26 |
+
i t
|
27 |
+
Ġ p
|
28 |
+
Ġ h
|
29 |
+
Ġa nd</w>
|
30 |
+
o n
|
31 |
+
in g</w>
|
32 |
+
a n
|
33 |
+
r o
|
34 |
+
Ġ m
|
35 |
+
Ġ d
|
36 |
+
e s</w>
|
37 |
+
Ġi n</w>
|
38 |
+
o n</w>
|
39 |
+
Ġt o</w>
|
40 |
+
o u
|
41 |
+
i s
|
42 |
+
Ġ a</w>
|
43 |
+
i c
|
44 |
+
Ġ T
|
45 |
+
a l
|
46 |
+
Ġ l
|
47 |
+
Ġ =</w>
|
48 |
+
Ġ re
|
49 |
+
Ġ "</w>
|
50 |
+
e s
|
51 |
+
Ġ S
|
52 |
+
a s</w>
|
53 |
+
a l</w>
|
54 |
+
i l
|
55 |
+
e l
|
56 |
+
i on</w>
|
57 |
+
Ġ A
|
58 |
+
Ġ C
|
59 |
+
Ġ 1
|
60 |
+
Ġ Ċ</w>
|
61 |
+
u r
|
62 |
+
ĠT h
|
63 |
+
Ġ n
|
64 |
+
a s
|
65 |
+
Ġ @
|
66 |
+
e c
|
67 |
+
o m
|
68 |
+
a c
|
69 |
+
Ġ e
|
70 |
+
Ġw as</w>
|
71 |
+
Ġ M
|
72 |
+
o r</w>
|
73 |
+
a n</w>
|
74 |
+
a m
|
75 |
+
e n</w>
|
76 |
+
o l
|
77 |
+
Ġ in
|
78 |
+
Ġ g
|
79 |
+
Ġ '</w>
|
80 |
+
Ġ B
|
81 |
+
l y</w>
|
82 |
+
a t</w>
|
83 |
+
i v
|
84 |
+
t s</w>
|
85 |
+
ĠTh e</w>
|
86 |
+
u s
|
87 |
+
- @</w>
|
88 |
+
Ġ@ -@</w>
|
89 |
+
i s</w>
|
90 |
+
Ġ I
|
91 |
+
Ġw h
|
92 |
+
i g
|
93 |
+
Ġ H
|
94 |
+
Ġs t
|
95 |
+
o s
|
96 |
+
u n
|
97 |
+
t h
|
98 |
+
Ġ P
|
99 |
+
Ġw it
|
100 |
+
Ġth at</w>
|
101 |
+
i r
|
102 |
+
Ġa s</w>
|
103 |
+
e m
|
104 |
+
Ġo n</w>
|
105 |
+
r a
|
106 |
+
Ġf or</w>
|
107 |
+
Ġ R
|
108 |
+
e t
|
109 |
+
o w
|
110 |
+
Ġ 2
|
111 |
+
i d
|
112 |
+
Ġ D
|
113 |
+
l e</w>
|
114 |
+
Ġwit h</w>
|
115 |
+
l a
|
116 |
+
en t</w>
|
117 |
+
i m
|
118 |
+
Ġ F
|
119 |
+
e a
|
120 |
+
i on
|
121 |
+
Ġb y</w>
|
122 |
+
Ġ )</w>
|
123 |
+
Ġ (</w>
|
124 |
+
Ġa l
|
125 |
+
Ġc on
|
126 |
+
en t
|
127 |
+
Ġ W
|
128 |
+
Ġi s</w>
|
129 |
+
er e</w>
|
130 |
+
Ġ G
|
131 |
+
Ġ N
|
132 |
+
Ġ L
|
133 |
+
Ġh a
|
134 |
+
er s</w>
|
135 |
+
r i
|
136 |
+
t h</w>
|
137 |
+
t ed</w>
|
138 |
+
u c
|
139 |
+
Ġ J
|
140 |
+
Ġ1 9
|
141 |
+
e v
|
142 |
+
u l
|
143 |
+
Ġ v
|
144 |
+
c e</w>
|
145 |
+
at ion</w>
|
146 |
+
ro m</w>
|
147 |
+
Ġb e
|
148 |
+
Ġ E
|
149 |
+
i n</w>
|
150 |
+
Ġth e
|
151 |
+
Ġf rom</w>
|
152 |
+
Ġ O
|
153 |
+
t er</w>
|
154 |
+
Ġp ro
|
155 |
+
Ġa r
|
156 |
+
a d
|
157 |
+
Ġc om
|
158 |
+
i c</w>
|
159 |
+
a g
|
160 |
+
Ġh is</w>
|
161 |
+
Ġs h
|
162 |
+
Ġa t</w>
|
163 |
+
o v
|
164 |
+
i es</w>
|
165 |
+
o o
|
166 |
+
p p
|
167 |
+
s t
|
168 |
+
c h
|
169 |
+
Ġ r
|
170 |
+
Ġ2 0
|
171 |
+
a y</w>
|
172 |
+
i f
|
173 |
+
Ġw ere</w>
|
174 |
+
Ġc h
|
175 |
+
u t</w>
|
176 |
+
s t</w>
|
177 |
+
u t
|
178 |
+
d s</w>
|
179 |
+
o p
|
180 |
+
u m
|
181 |
+
Ġi t</w>
|
182 |
+
o c
|
183 |
+
t er
|
184 |
+
l e
|
185 |
+
ig h
|
186 |
+
u d
|
187 |
+
Ġe x
|
188 |
+
ion s</w>
|
189 |
+
at e</w>
|
190 |
+
it y</w>
|
191 |
+
at ed</w>
|
192 |
+
Ġ un
|
193 |
+
e p
|
194 |
+
q u
|
195 |
+
Ġn o
|
196 |
+
Ġ K
|
197 |
+
iv e</w>
|
198 |
+
is t
|
199 |
+
Ġo n
|
200 |
+
am e</w>
|
201 |
+
ou n
|
202 |
+
i r</w>
|
203 |
+
a b
|
204 |
+
Ġ â
|
205 |
+
in g
|
206 |
+
Ġh e</w>
|
207 |
+
l d</w>
|
208 |
+
u g
|
209 |
+
ic h</w>
|
210 |
+
Ġa n</w>
|
211 |
+
e d
|
212 |
+
Ġ k
|
213 |
+
Ġâ Ģ
|
214 |
+
Ġha d</w>
|
215 |
+
v e</w>
|
216 |
+
a in
|
217 |
+
Ġs e
|
218 |
+
t ion</w>
|
219 |
+
or e</w>
|
220 |
+
re s
|
221 |
+
Ġwh ich</w>
|
222 |
+
ĠI n</w>
|
223 |
+
o d
|
224 |
+
th er</w>
|
225 |
+
a k
|
226 |
+
Ġs p
|
227 |
+
a r</w>
|
228 |
+
Ġ y
|
229 |
+
ĠC h
|
230 |
+
on g</w>
|
231 |
+
Ġa c
|
232 |
+
es t</w>
|
233 |
+
Ġ U
|
234 |
+
a p
|
235 |
+
f f
|
236 |
+
al ly</w>
|
237 |
+
r it
|
238 |
+
ĠS t
|
239 |
+
u b
|
240 |
+
g e</w>
|
241 |
+
b er</w>
|
242 |
+
e t</w>
|
243 |
+
Ġb e</w>
|
244 |
+
e ar
|
245 |
+
Ġre c
|
246 |
+
er s
|
247 |
+
Ġf ir
|
248 |
+
o t
|
249 |
+
Ġar e</w>
|
250 |
+
Ġa n
|
251 |
+
c h</w>
|
252 |
+
o g
|
253 |
+
i a</w>
|
254 |
+
es t
|
255 |
+
in e</w>
|
256 |
+
il l
|
257 |
+
an d
|
258 |
+
e l</w>
|
259 |
+
ar y</w>
|
260 |
+
e w</w>
|
261 |
+
i d</w>
|
262 |
+
Ġf or
|
263 |
+
Ġ ;</w>
|
264 |
+
Ġcom p
|
265 |
+
Ġ V
|
266 |
+
Ġin c
|
267 |
+
t r
|
268 |
+
Ġ20 0
|
269 |
+
Ġthe ir</w>
|
270 |
+
u s</w>
|
271 |
+
Ġb ut</w>
|
272 |
+
r an
|
273 |
+
ic al</w>
|
274 |
+
Ġfir st</w>
|
275 |
+
Ġd e
|
276 |
+
Ġin t
|
277 |
+
Ġ ro
|
278 |
+
s o</w>
|
279 |
+
ĠâĢ ĵ</w>
|
280 |
+
Ġno t</w>
|
281 |
+
d ing</w>
|
282 |
+
f ter</w>
|
283 |
+
ur e</w>
|
284 |
+
Ġp ar
|
285 |
+
Ġ :</w>
|
286 |
+
i an</w>
|
287 |
+
Ġt w
|
288 |
+
ou ld</w>
|
289 |
+
Ġal so</w>
|
290 |
+
Ġi ts</w>
|
291 |
+
Ġw or
|
292 |
+
u m</w>
|
293 |
+
Ġo r</w>
|
294 |
+
os t</w>
|
295 |
+
0 0</w>
|
296 |
+
ou r
|
297 |
+
ar d</w>
|
298 |
+
Ġre s
|
299 |
+
m p
|
300 |
+
u e</w>
|
301 |
+
Ġa b
|
302 |
+
is h</w>
|
303 |
+
Ġcon t
|
304 |
+
Ġa d
|
305 |
+
ow n</w>
|
306 |
+
al l</w>
|
307 |
+
ou g
|
308 |
+
Ġh er</w>
|
309 |
+
as t</w>
|
310 |
+
Ġ en
|
311 |
+
om e</w>
|
312 |
+
al l
|
313 |
+
d ed</w>
|
314 |
+
o w</w>
|
315 |
+
Ġha ve</w>
|
316 |
+
Ġ us
|
317 |
+
ea r</w>
|
318 |
+
ac k</w>
|
319 |
+
d uc
|
320 |
+
i al</w>
|
321 |
+
s s
|
322 |
+
en ts</w>
|
323 |
+
a in</w>
|
324 |
+
t ing</w>
|
325 |
+
Ġon e</w>
|
326 |
+
es s
|
327 |
+
Ġh as</w>
|
328 |
+
igh t</w>
|
329 |
+
a v
|
330 |
+
Ġe v
|
331 |
+
ou t</w>
|
332 |
+
a y
|
333 |
+
en ce</w>
|
334 |
+
Ġbe en</w>
|
335 |
+
e w
|
336 |
+
Ġtw o</w>
|
337 |
+
Ġc l
|
338 |
+
d er</w>
|
339 |
+
im e</w>
|
340 |
+
k s</w>
|
341 |
+
es s</w>
|
342 |
+
is h
|
343 |
+
. @</w>
|
344 |
+
Ġ@ .@</w>
|
345 |
+
Ġp la
|
346 |
+
Ġp l
|
347 |
+
Ġo r
|
348 |
+
u p</w>
|
349 |
+
m ent</w>
|
350 |
+
ur ing</w>
|
351 |
+
ol l
|
352 |
+
ĠI n
|
353 |
+
Ġth is</w>
|
354 |
+
Ġb ec
|
355 |
+
Ġcom m
|
356 |
+
Ġd is
|
357 |
+
at er</w>
|
358 |
+
ag e</w>
|
359 |
+
Ġa pp
|
360 |
+
ou s</w>
|
361 |
+
e y</w>
|
362 |
+
i l</w>
|
363 |
+
p er
|
364 |
+
ĠA l
|
365 |
+
ion al</w>
|
366 |
+
l ud
|
367 |
+
el y</w>
|
368 |
+
t t
|
369 |
+
il e</w>
|
370 |
+
i z
|
371 |
+
Ġ j
|
372 |
+
Ġwh o</w>
|
373 |
+
Ġa g
|
374 |
+
i b
|
375 |
+
Ġthe y</w>
|
376 |
+
f or
|
377 |
+
Ġo v
|
378 |
+
at h
|
379 |
+
e g
|
380 |
+
Ġs c
|
381 |
+
i p
|
382 |
+
Ġ20 1
|
383 |
+
Ġ 3
|
384 |
+
Ġp er
|
385 |
+
or y</w>
|
386 |
+
Ġd es
|
387 |
+
id e</w>
|
388 |
+
Ġs er
|
389 |
+
s e</w>
|
390 |
+
ĠH e</w>
|
391 |
+
la nd</w>
|
392 |
+
at ions</w>
|
393 |
+
r ic
|
394 |
+
i t</w>
|
395 |
+
re s</w>
|
396 |
+
er ed</w>
|
397 |
+
Ġp re
|
398 |
+
ĠS h
|
399 |
+
an ce</w>
|
400 |
+
or t</w>
|
401 |
+
an t</w>
|
402 |
+
, @</w>
|
403 |
+
Ġ@ ,@</w>
|
404 |
+
el l</w>
|
405 |
+
Ġ Y
|
406 |
+
n ed</w>
|
407 |
+
el l
|
408 |
+
it e</w>
|
409 |
+
Ġinc lud
|
410 |
+
Ġre p
|
411 |
+
Ġa fter</w>
|
412 |
+
Ġs uc
|
413 |
+
re e</w>
|
414 |
+
an y</w>
|
415 |
+
i m</w>
|
416 |
+
or t
|
417 |
+
Ġ1 8
|
418 |
+
Ġs u
|
419 |
+
ad e</w>
|
420 |
+
ou r</w>
|
421 |
+
ĠU n
|
422 |
+
ĠI t</w>
|
423 |
+
i k
|
424 |
+
ĠM ar
|
425 |
+
em ber</w>
|
426 |
+
Ġ 1</w>
|
427 |
+
e en</w>
|
428 |
+
a nd</w>
|
429 |
+
Ġs ec
|
430 |
+
ic e</w>
|
431 |
+
Ġt ime</w>
|
432 |
+
ĠA n
|
433 |
+
Ġint o</w>
|
434 |
+
Ġf in
|
435 |
+
Ġo ther</w>
|
436 |
+
Ġa tt
|
437 |
+
il l</w>
|
438 |
+
re n
|
439 |
+
ac h
|
440 |
+
as s
|
441 |
+
er al</w>
|
442 |
+
es e</w>
|
443 |
+
s h
|
444 |
+
al s</w>
|
445 |
+
it ion</w>
|
446 |
+
oug h</w>
|
447 |
+
l es</w>
|
448 |
+
am p
|
449 |
+
Ġw ould</w>
|
450 |
+
Ġm ore</w>
|
451 |
+
ro ug
|
452 |
+
ri b
|
453 |
+
er y</w>
|
454 |
+
ac e</w>
|
455 |
+
Ġ A</w>
|
456 |
+
Ġpla y
|
457 |
+
it ed</w>
|
458 |
+
k ed</w>
|
459 |
+
is t</w>
|
460 |
+
i ed</w>
|
461 |
+
Ġ 2</w>
|
462 |
+
as ed</w>
|
463 |
+
ing s</w>
|
464 |
+
an g
|
465 |
+
a m</w>
|
466 |
+
i p</w>
|
467 |
+
Ġb o
|
468 |
+
ab le</w>
|
469 |
+
t y</w>
|
470 |
+
Ġch ar
|
471 |
+
Ġc ent
|
472 |
+
et w
|
473 |
+
at es</w>
|
474 |
+
ro p
|
475 |
+
Ġ I</w>
|
476 |
+
u nd</w>
|
477 |
+
ĠA m
|
478 |
+
c es</w>
|
479 |
+
o in
|
480 |
+
Ġin ter
|
481 |
+
u p
|
482 |
+
c t
|
483 |
+
on e</w>
|
484 |
+
Ġt ra
|
485 |
+
an t
|
486 |
+
ec t
|
487 |
+
Ġal l</w>
|
488 |
+
e f
|
489 |
+
Ġcon s
|
490 |
+
ub l
|
491 |
+
n ing</w>
|
492 |
+
an s</w>
|
493 |
+
Ġf e
|
494 |
+
us t</w>
|
495 |
+
Ġ 0
|
496 |
+
Ġre m
|
497 |
+
as e</w>
|
498 |
+
on g
|
499 |
+
Ġwh en</w>
|
500 |
+
e b
|
501 |
+
ĠW h
|
502 |
+
Ġe ar
|
503 |
+
ev er</w>
|
504 |
+
Ġov er</w>
|
505 |
+
Ġk n
|
506 |
+
a us
|
507 |
+
Ġp os
|
508 |
+
a d</w>
|
509 |
+
er m
|
510 |
+
Ġsh e</w>
|
511 |
+
Ġ ra
|
512 |
+
Ġd uring</w>
|
513 |
+
as on</w>
|
514 |
+
v i
|
515 |
+
Ġex p
|
516 |
+
Ġl ea
|
517 |
+
Ġ el
|
518 |
+
Ġ 4
|
519 |
+
Ġon ly</w>
|
520 |
+
o nd</w>
|
521 |
+
Ġd ec
|
522 |
+
Ġac c
|
523 |
+
Ġo ff
|
524 |
+
is s
|
525 |
+
Ġf l
|
526 |
+
ĠE n
|
527 |
+
o t</w>
|
528 |
+
en s
|
529 |
+
os e</w>
|
530 |
+
ak e</w>
|
531 |
+
o m</w>
|
532 |
+
Ġs ev
|
533 |
+
ac h</w>
|
534 |
+
etw een</w>
|
535 |
+
er n
|
536 |
+
Ġ 3</w>
|
537 |
+
Ġp r
|
538 |
+
Ġg ro
|
539 |
+
r uc
|
540 |
+
Ġd i
|
541 |
+
Ġ19 9
|
542 |
+
ĠA r
|
543 |
+
Ġg ame</w>
|
544 |
+
Ġh im</w>
|
545 |
+
oo k</w>
|
546 |
+
Ġ up</w>
|
547 |
+
Ġab out</w>
|
548 |
+
Ġre l
|
549 |
+
for m
|
550 |
+
Ġth ree</w>
|
551 |
+
at t
|
552 |
+
ĠC om
|
553 |
+
Ġs a
|
554 |
+
ear s</w>
|
555 |
+
Ġ 5
|
556 |
+
r y</w>
|
557 |
+
Ġi mp
|
558 |
+
Ġm ost</w>
|
559 |
+
f er
|
560 |
+
Ġp res
|
561 |
+
Ġf il
|
562 |
+
Ġb etween</w>
|
563 |
+
Ġbe g
|
564 |
+
p h
|
565 |
+
or s</w>
|
566 |
+
Ġth an</w>
|
567 |
+
Ġrec or
|
568 |
+
o b
|
569 |
+
er ic
|
570 |
+
at ing</w>
|
571 |
+
Ġth roug
|
572 |
+
k ing</w>
|
573 |
+
Ġo ut</w>
|
574 |
+
Ġn um
|
575 |
+
oo d</w>
|
576 |
+
oll ow
|
577 |
+
ac t
|
578 |
+
u il
|
579 |
+
Ġc re
|
580 |
+
ol og
|
581 |
+
at ional</w>
|
582 |
+
Ġpro duc
|
583 |
+
Ġwh ile</w>
|
584 |
+
Ġl ater</w>
|
585 |
+
Ġw rit
|
586 |
+
e x
|
587 |
+
Ġst ar
|
588 |
+
Ġsp ec
|
589 |
+
e e
|
590 |
+
ish ed</w>
|
591 |
+
Ġre g
|
592 |
+
is ion</w>
|
593 |
+
ou th</w>
|
594 |
+
Ġre le
|
595 |
+
Ġa ss
|
596 |
+
Ġse ason</w>
|
597 |
+
Ġm ade</w>
|
598 |
+
il y</w>
|
599 |
+
r u
|
600 |
+
o y
|
601 |
+
t ur
|
602 |
+
t e</w>
|
603 |
+
Ġ qu
|
604 |
+
Ġm ov
|
605 |
+
ur y</w>
|
606 |
+
ĠAm eric
|
607 |
+
em ent</w>
|
608 |
+
c c
|
609 |
+
ou nd</w>
|
610 |
+
Ġl ar
|
611 |
+
Ġfor m
|
612 |
+
ec t</w>
|
613 |
+
Ġde f
|
614 |
+
Ġm us
|
615 |
+
ĠP ar
|
616 |
+
Ġm e
|
617 |
+
Ġs ub
|
618 |
+
w ay</w>
|
619 |
+
o p</w>
|
620 |
+
o h
|
621 |
+
el d</w>
|
622 |
+
i e</w>
|
623 |
+
em p
|
624 |
+
am es</w>
|
625 |
+
er n</w>
|
626 |
+
Ġn or
|
627 |
+
iv ed</w>
|
628 |
+
ev el
|
629 |
+
Ġsuc h</w>
|
630 |
+
ar ds</w>
|
631 |
+
Ġin d
|
632 |
+
ik e</w>
|
633 |
+
Ġg en
|
634 |
+
er t
|
635 |
+
Ġy ear</w>
|
636 |
+
Ġus ed</w>
|
637 |
+
Ġn ew</w>
|
638 |
+
Ġ 5</w>
|
639 |
+
Ġal b
|
640 |
+
s p
|
641 |
+
y p
|
642 |
+
Ġwit h
|
643 |
+
Ġwh ere</w>
|
644 |
+
ic s</w>
|
645 |
+
ĠTh is</w>
|
646 |
+
Ġthe m</w>
|
647 |
+
w n</w>
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,1740 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|