Upload merges.txt with huggingface_hub
Browse files- merges.txt +329 -0
merges.txt
ADDED
|
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
+
Ġ t
|
| 3 |
+
i n
|
| 4 |
+
e n
|
| 5 |
+
Ġ a
|
| 6 |
+
e r
|
| 7 |
+
e s
|
| 8 |
+
Ġ o
|
| 9 |
+
Ġt o
|
| 10 |
+
a n
|
| 11 |
+
in g
|
| 12 |
+
a r
|
| 13 |
+
a t
|
| 14 |
+
h e
|
| 15 |
+
i s
|
| 16 |
+
o r
|
| 17 |
+
Ġ m
|
| 18 |
+
Ġ s
|
| 19 |
+
a l
|
| 20 |
+
k en
|
| 21 |
+
o n
|
| 22 |
+
Ġto ken
|
| 23 |
+
l e
|
| 24 |
+
Ġo f
|
| 25 |
+
Ġ b
|
| 26 |
+
Ġ p
|
| 27 |
+
i t
|
| 28 |
+
o u
|
| 29 |
+
Ġ c
|
| 30 |
+
Ġ f
|
| 31 |
+
Ġa n
|
| 32 |
+
i c
|
| 33 |
+
i z
|
| 34 |
+
i on
|
| 35 |
+
r o
|
| 36 |
+
e d
|
| 37 |
+
e l
|
| 38 |
+
r e
|
| 39 |
+
Ġ in
|
| 40 |
+
Ġt he
|
| 41 |
+
Ġ is
|
| 42 |
+
Ġan d
|
| 43 |
+
Ġ T
|
| 44 |
+
Ġ u
|
| 45 |
+
Ġb e
|
| 46 |
+
Ġ d
|
| 47 |
+
Ġt h
|
| 48 |
+
a c
|
| 49 |
+
m p
|
| 50 |
+
o d
|
| 51 |
+
Ġ w
|
| 52 |
+
Ġ le
|
| 53 |
+
en c
|
| 54 |
+
en t
|
| 55 |
+
Ġtoken iz
|
| 56 |
+
a s
|
| 57 |
+
e x
|
| 58 |
+
t er
|
| 59 |
+
Ġ l
|
| 60 |
+
ar n
|
| 61 |
+
Ġtoken s
|
| 62 |
+
Ġp ro
|
| 63 |
+
q u
|
| 64 |
+
u l
|
| 65 |
+
Ġ h
|
| 66 |
+
Ġ v
|
| 67 |
+
at ion
|
| 68 |
+
Ġth at
|
| 69 |
+
Ġle arn
|
| 70 |
+
a in
|
| 71 |
+
c es
|
| 72 |
+
e c
|
| 73 |
+
f ic
|
| 74 |
+
g e
|
| 75 |
+
i l
|
| 76 |
+
r es
|
| 77 |
+
u a
|
| 78 |
+
y ou
|
| 79 |
+
Ġ n
|
| 80 |
+
Ġ re
|
| 81 |
+
Ġ you
|
| 82 |
+
Ġt r
|
| 83 |
+
Ġt ex
|
| 84 |
+
Ġu n
|
| 85 |
+
ces s
|
| 86 |
+
Ġtex t
|
| 87 |
+
0 0
|
| 88 |
+
a m
|
| 89 |
+
d s
|
| 90 |
+
e m
|
| 91 |
+
e t
|
| 92 |
+
g ua
|
| 93 |
+
i fic
|
| 94 |
+
o c
|
| 95 |
+
p er
|
| 96 |
+
s t
|
| 97 |
+
u r
|
| 98 |
+
v e
|
| 99 |
+
Ġo n
|
| 100 |
+
an gua
|
| 101 |
+
or ds
|
| 102 |
+
Ġm od
|
| 103 |
+
enc e
|
| 104 |
+
Ġtokeniz er
|
| 105 |
+
ul ar
|
| 106 |
+
Ġlearn ing
|
| 107 |
+
ain ing
|
| 108 |
+
a b
|
| 109 |
+
c h
|
| 110 |
+
f or
|
| 111 |
+
h in
|
| 112 |
+
h is
|
| 113 |
+
i al
|
| 114 |
+
i mp
|
| 115 |
+
k s
|
| 116 |
+
s e
|
| 117 |
+
s u
|
| 118 |
+
u s
|
| 119 |
+
Ġ B
|
| 120 |
+
Ġ [
|
| 121 |
+
Ġ imp
|
| 122 |
+
Ġa r
|
| 123 |
+
Ġo r
|
| 124 |
+
an s
|
| 125 |
+
at e
|
| 126 |
+
it h
|
| 127 |
+
Ġc an
|
| 128 |
+
Ġf or
|
| 129 |
+
ac hin
|
| 130 |
+
Ġw ords
|
| 131 |
+
Ġl angua
|
| 132 |
+
Ġpro cess
|
| 133 |
+
Ġyou r
|
| 134 |
+
ur al
|
| 135 |
+
Ġmod el
|
| 136 |
+
achin e
|
| 137 |
+
L P
|
| 138 |
+
N LP
|
| 139 |
+
P E
|
| 140 |
+
T he
|
| 141 |
+
] ,
|
| 142 |
+
a d
|
| 143 |
+
d ed
|
| 144 |
+
e v
|
| 145 |
+
g h
|
| 146 |
+
i d
|
| 147 |
+
i m
|
| 148 |
+
l d
|
| 149 |
+
l p
|
| 150 |
+
l u
|
| 151 |
+
l y
|
| 152 |
+
p l
|
| 153 |
+
t e
|
| 154 |
+
t ion
|
| 155 |
+
t ific
|
| 156 |
+
u m
|
| 157 |
+
v is
|
| 158 |
+
w n
|
| 159 |
+
y te
|
| 160 |
+
Ġ en
|
| 161 |
+
Ġ he
|
| 162 |
+
Ġ it
|
| 163 |
+
Ġ qu
|
| 164 |
+
ar t
|
| 165 |
+
at a
|
| 166 |
+
or p
|
| 167 |
+
Ġm u
|
| 168 |
+
Ġm an
|
| 169 |
+
Ġs u
|
| 170 |
+
on t
|
| 171 |
+
it y
|
| 172 |
+
ou t
|
| 173 |
+
Ġc orp
|
| 174 |
+
Ġc ont
|
| 175 |
+
ion s
|
| 176 |
+
el l
|
| 177 |
+
Ġin t
|
| 178 |
+
ĠT he
|
| 179 |
+
Ġd ata
|
| 180 |
+
Ġw ith
|
| 181 |
+
Ġv al
|
| 182 |
+
Ġv oc
|
| 183 |
+
Ġtr aining
|
| 184 |
+
Ġtr ans
|
| 185 |
+
per vis
|
| 186 |
+
ab ular
|
| 187 |
+
for m
|
| 188 |
+
Ġar tific
|
| 189 |
+
Ġlangua ge
|
| 190 |
+
Ġmodel s
|
| 191 |
+
Ġvoc abular
|
| 192 |
+
pervis ed
|
| 193 |
+
Ġartific ial
|
| 194 |
+
B PE
|
| 195 |
+
B yte
|
| 196 |
+
M achine
|
| 197 |
+
T his
|
| 198 |
+
a k
|
| 199 |
+
a mp
|
| 200 |
+
a ve
|
| 201 |
+
c lu
|
| 202 |
+
d ing
|
| 203 |
+
d ded
|
| 204 |
+
e en
|
| 205 |
+
e qu
|
| 206 |
+
e ural
|
| 207 |
+
g r
|
| 208 |
+
g ence
|
| 209 |
+
h er
|
| 210 |
+
h es
|
| 211 |
+
i es
|
| 212 |
+
i ve
|
| 213 |
+
i gence
|
| 214 |
+
k n
|
| 215 |
+
l ions
|
| 216 |
+
m s
|
| 217 |
+
m al
|
| 218 |
+
o m
|
| 219 |
+
o o
|
| 220 |
+
o p
|
| 221 |
+
o mp
|
| 222 |
+
o wn
|
| 223 |
+
p p
|
| 224 |
+
p ic
|
| 225 |
+
p ec
|
| 226 |
+
p res
|
| 227 |
+
t s
|
| 228 |
+
t w
|
| 229 |
+
t en
|
| 230 |
+
t an
|
| 231 |
+
t ing
|
| 232 |
+
u t
|
| 233 |
+
u ter
|
| 234 |
+
v er
|
| 235 |
+
v el
|
| 236 |
+
v id
|
| 237 |
+
w or
|
| 238 |
+
y pic
|
| 239 |
+
Ġ (
|
| 240 |
+
Ġ 2
|
| 241 |
+
Ġ I
|
| 242 |
+
Ġ L
|
| 243 |
+
Ġ P
|
| 244 |
+
Ġ r
|
| 245 |
+
Ġ ex
|
| 246 |
+
Ġ NLP
|
| 247 |
+
Ġt as
|
| 248 |
+
Ġa l
|
| 249 |
+
Ġa t
|
| 250 |
+
Ġa re
|
| 251 |
+
Ġa dded
|
| 252 |
+
an d
|
| 253 |
+
at ural
|
| 254 |
+
or tan
|
| 255 |
+
Ġm achine
|
| 256 |
+
Ġm ak
|
| 257 |
+
Ġs iz
|
| 258 |
+
Ġs ent
|
| 259 |
+
Ġs amp
|
| 260 |
+
Ġs equ
|
| 261 |
+
Ġs mal
|
| 262 |
+
al le
|
| 263 |
+
le vel
|
| 264 |
+
Ġof ten
|
| 265 |
+
Ġb ro
|
| 266 |
+
Ġp art
|
| 267 |
+
ou s
|
| 268 |
+
ou gh
|
| 269 |
+
Ġc omp
|
| 270 |
+
Ġf ro
|
| 271 |
+
Ġf am
|
| 272 |
+
Ġf oc
|
| 273 |
+
Ġin clu
|
| 274 |
+
ĠT his
|
| 275 |
+
ĠT hes
|
| 276 |
+
ĠT oo
|
| 277 |
+
Ġu s
|
| 278 |
+
Ġu se
|
| 279 |
+
Ġbe tw
|
| 280 |
+
Ġd i
|
| 281 |
+
od ing
|
| 282 |
+
enc es
|
| 283 |
+
Ġtokeniz ation
|
| 284 |
+
as ed
|
| 285 |
+
Ġl ar
|
| 286 |
+
Ġpro gr
|
| 287 |
+
Ġpro vid
|
| 288 |
+
Ġh um
|
| 289 |
+
Ġh ave
|
| 290 |
+
ec t
|
| 291 |
+
il lions
|
| 292 |
+
Ġn et
|
| 293 |
+
Ġn eural
|
| 294 |
+
Ġre pres
|
| 295 |
+
Ġun kn
|
| 296 |
+
00 0
|
| 297 |
+
su pervised
|
| 298 |
+
us es
|
| 299 |
+
ĠB BPE
|
| 300 |
+
Ġimp ortan
|
| 301 |
+
pl ic
|
| 302 |
+
Ġen su
|
| 303 |
+
Ġhe lp
|
| 304 |
+
Ġmu ch
|
| 305 |
+
Ġman y
|
| 306 |
+
Ġsu b
|
| 307 |
+
Ġcorp us
|
| 308 |
+
ell igence
|
| 309 |
+
Ġint elligence
|
| 310 |
+
Ġwith out
|
| 311 |
+
Ġtrans form
|
| 312 |
+
Ġvocabular y
|
| 313 |
+
wor ks
|
| 314 |
+
ypic al
|
| 315 |
+
Ġtas ks
|
| 316 |
+
Ġsamp le
|
| 317 |
+
Ġsmal l
|
| 318 |
+
Ġcomp uter
|
| 319 |
+
Ġfro m
|
| 320 |
+
Ġfoc uses
|
| 321 |
+
ĠThes e
|
| 322 |
+
Ġbetw een
|
| 323 |
+
Ġprogr am
|
| 324 |
+
Ġprovid es
|
| 325 |
+
Ġnet works
|
| 326 |
+
Ġrepres ent
|
| 327 |
+
Ġunkn own
|
| 328 |
+
Ġimportan t
|
| 329 |
+
Ġtransform er
|