Upload folder using huggingface_hub
Browse files- fw57M_Entropy_thresholdM_500/merges.txt +243 -0
- fw57M_Entropy_thresholdM_500/special_tokens_map.json +5 -0
- fw57M_Entropy_thresholdM_500/stats.csv +0 -0
- fw57M_Entropy_thresholdM_500/tokenizer.json +1533 -0
- fw57M_Entropy_thresholdM_500/tokenizer_config.json +29 -0
- fw57M_Entropy_thresholdM_500/vocab.json +1 -0
fw57M_Entropy_thresholdM_500/merges.txt
ADDED
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#version: 0.2
|
2 |
+
n g
|
3 |
+
e r
|
4 |
+
u r
|
5 |
+
h e
|
6 |
+
n d
|
7 |
+
s s
|
8 |
+
g h
|
9 |
+
g e
|
10 |
+
e n
|
11 |
+
g r
|
12 |
+
u p
|
13 |
+
k e
|
14 |
+
d y
|
15 |
+
d e
|
16 |
+
n t
|
17 |
+
r d
|
18 |
+
d g
|
19 |
+
v e
|
20 |
+
r t
|
21 |
+
a r
|
22 |
+
p l
|
23 |
+
i n
|
24 |
+
l d
|
25 |
+
r g
|
26 |
+
l y
|
27 |
+
r o
|
28 |
+
e d
|
29 |
+
a n
|
30 |
+
m b
|
31 |
+
t e
|
32 |
+
n c
|
33 |
+
l e
|
34 |
+
e l
|
35 |
+
u l
|
36 |
+
u s
|
37 |
+
y m
|
38 |
+
q u
|
39 |
+
g u
|
40 |
+
l l
|
41 |
+
w n
|
42 |
+
r k
|
43 |
+
h er
|
44 |
+
u m
|
45 |
+
i g
|
46 |
+
e s
|
47 |
+
c e
|
48 |
+
e m
|
49 |
+
i b
|
50 |
+
t r
|
51 |
+
o n
|
52 |
+
c l
|
53 |
+
m a
|
54 |
+
s e
|
55 |
+
l i
|
56 |
+
m e
|
57 |
+
t h
|
58 |
+
b l
|
59 |
+
d en
|
60 |
+
g n
|
61 |
+
o w
|
62 |
+
r c
|
63 |
+
a t
|
64 |
+
e t
|
65 |
+
c h
|
66 |
+
d u
|
67 |
+
u d
|
68 |
+
a l
|
69 |
+
u c
|
70 |
+
u g
|
71 |
+
i v
|
72 |
+
b u
|
73 |
+
a nd
|
74 |
+
u t
|
75 |
+
s h
|
76 |
+
l a
|
77 |
+
e c
|
78 |
+
i o
|
79 |
+
a rd
|
80 |
+
r a
|
81 |
+
o m
|
82 |
+
o u
|
83 |
+
o g
|
84 |
+
c t
|
85 |
+
o up
|
86 |
+
v i
|
87 |
+
d ro
|
88 |
+
t i
|
89 |
+
e nt
|
90 |
+
c k
|
91 |
+
pl e
|
92 |
+
u e
|
93 |
+
i ng
|
94 |
+
ma l
|
95 |
+
o r
|
96 |
+
p o
|
97 |
+
r e
|
98 |
+
l t
|
99 |
+
r n
|
100 |
+
s t
|
101 |
+
o d
|
102 |
+
r m
|
103 |
+
a g
|
104 |
+
s k
|
105 |
+
e a
|
106 |
+
t o
|
107 |
+
i l
|
108 |
+
b i
|
109 |
+
th e
|
110 |
+
e y
|
111 |
+
u nd
|
112 |
+
i a
|
113 |
+
h i
|
114 |
+
r i
|
115 |
+
ug h
|
116 |
+
a m
|
117 |
+
c a
|
118 |
+
g et
|
119 |
+
i t
|
120 |
+
i c
|
121 |
+
a k
|
122 |
+
h t
|
123 |
+
r v
|
124 |
+
b ut
|
125 |
+
a y
|
126 |
+
n a
|
127 |
+
a s
|
128 |
+
a d
|
129 |
+
n ce
|
130 |
+
u n
|
131 |
+
n s
|
132 |
+
s u
|
133 |
+
i r
|
134 |
+
t y
|
135 |
+
o v
|
136 |
+
t u
|
137 |
+
o y
|
138 |
+
a p
|
139 |
+
g d
|
140 |
+
i p
|
141 |
+
ro m
|
142 |
+
t ur
|
143 |
+
ec t
|
144 |
+
f f
|
145 |
+
i on
|
146 |
+
i m
|
147 |
+
l o
|
148 |
+
p t
|
149 |
+
u se
|
150 |
+
u i
|
151 |
+
i sh
|
152 |
+
n e
|
153 |
+
d i
|
154 |
+
a v
|
155 |
+
g a
|
156 |
+
n o
|
157 |
+
o p
|
158 |
+
ge r
|
159 |
+
i s
|
160 |
+
d rom
|
161 |
+
i e
|
162 |
+
w e
|
163 |
+
p h
|
164 |
+
d a
|
165 |
+
r r
|
166 |
+
m at
|
167 |
+
m o
|
168 |
+
b e
|
169 |
+
a i
|
170 |
+
i d
|
171 |
+
ll y
|
172 |
+
gr a
|
173 |
+
u re
|
174 |
+
l er
|
175 |
+
a c
|
176 |
+
h a
|
177 |
+
d er
|
178 |
+
d o
|
179 |
+
n k
|
180 |
+
ag e
|
181 |
+
s i
|
182 |
+
m p
|
183 |
+
d l
|
184 |
+
ig h
|
185 |
+
b a
|
186 |
+
o l
|
187 |
+
u a
|
188 |
+
a b
|
189 |
+
the r
|
190 |
+
e ss
|
191 |
+
rd e
|
192 |
+
ve l
|
193 |
+
n i
|
194 |
+
t em
|
195 |
+
r ch
|
196 |
+
l em
|
197 |
+
c i
|
198 |
+
m u
|
199 |
+
b er
|
200 |
+
m en
|
201 |
+
o s
|
202 |
+
m n
|
203 |
+
k o
|
204 |
+
a se
|
205 |
+
ve r
|
206 |
+
o o
|
207 |
+
d r
|
208 |
+
i de
|
209 |
+
r ap
|
210 |
+
a te
|
211 |
+
e st
|
212 |
+
r ty
|
213 |
+
v a
|
214 |
+
c u
|
215 |
+
e e
|
216 |
+
p e
|
217 |
+
l f
|
218 |
+
f t
|
219 |
+
h o
|
220 |
+
t t
|
221 |
+
t a
|
222 |
+
e g
|
223 |
+
i cl
|
224 |
+
l io
|
225 |
+
m i
|
226 |
+
c er
|
227 |
+
y l
|
228 |
+
o k
|
229 |
+
o rk
|
230 |
+
k a
|
231 |
+
f e
|
232 |
+
r y
|
233 |
+
ul t
|
234 |
+
l tur
|
235 |
+
l u
|
236 |
+
r am
|
237 |
+
e the
|
238 |
+
e v
|
239 |
+
n at
|
240 |
+
r s
|
241 |
+
t l
|
242 |
+
gh t
|
243 |
+
t ion
|
fw57M_Entropy_thresholdM_500/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|padding|>"
|
5 |
+
}
|
fw57M_Entropy_thresholdM_500/stats.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
fw57M_Entropy_thresholdM_500/tokenizer.json
ADDED
@@ -0,0 +1,1533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<|padding|>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"normalizer": {
|
26 |
+
"type": "Sequence",
|
27 |
+
"normalizers": [
|
28 |
+
{
|
29 |
+
"type": "NFD"
|
30 |
+
}
|
31 |
+
]
|
32 |
+
},
|
33 |
+
"pre_tokenizer": {
|
34 |
+
"type": "ByteLevel",
|
35 |
+
"add_prefix_space": true,
|
36 |
+
"trim_offsets": true,
|
37 |
+
"use_regex": true
|
38 |
+
},
|
39 |
+
"post_processor": {
|
40 |
+
"type": "ByteLevel",
|
41 |
+
"add_prefix_space": true,
|
42 |
+
"trim_offsets": true,
|
43 |
+
"use_regex": true
|
44 |
+
},
|
45 |
+
"decoder": {
|
46 |
+
"type": "ByteLevel",
|
47 |
+
"add_prefix_space": true,
|
48 |
+
"trim_offsets": true,
|
49 |
+
"use_regex": true
|
50 |
+
},
|
51 |
+
"model": {
|
52 |
+
"type": "BPE",
|
53 |
+
"dropout": null,
|
54 |
+
"unk_token": null,
|
55 |
+
"continuing_subword_prefix": null,
|
56 |
+
"end_of_word_suffix": null,
|
57 |
+
"fuse_unk": false,
|
58 |
+
"byte_fallback": false,
|
59 |
+
"ignore_merges": false,
|
60 |
+
"vocab": {
|
61 |
+
"<|padding|>": 0,
|
62 |
+
"<|endoftext|>": 1,
|
63 |
+
"!": 2,
|
64 |
+
"\"": 3,
|
65 |
+
"#": 4,
|
66 |
+
"$": 5,
|
67 |
+
"%": 6,
|
68 |
+
"&": 7,
|
69 |
+
"'": 8,
|
70 |
+
"(": 9,
|
71 |
+
")": 10,
|
72 |
+
"*": 11,
|
73 |
+
"+": 12,
|
74 |
+
",": 13,
|
75 |
+
"-": 14,
|
76 |
+
".": 15,
|
77 |
+
"/": 16,
|
78 |
+
"0": 17,
|
79 |
+
"1": 18,
|
80 |
+
"2": 19,
|
81 |
+
"3": 20,
|
82 |
+
"4": 21,
|
83 |
+
"5": 22,
|
84 |
+
"6": 23,
|
85 |
+
"7": 24,
|
86 |
+
"8": 25,
|
87 |
+
"9": 26,
|
88 |
+
":": 27,
|
89 |
+
";": 28,
|
90 |
+
"<": 29,
|
91 |
+
"=": 30,
|
92 |
+
">": 31,
|
93 |
+
"?": 32,
|
94 |
+
"@": 33,
|
95 |
+
"A": 34,
|
96 |
+
"B": 35,
|
97 |
+
"C": 36,
|
98 |
+
"D": 37,
|
99 |
+
"E": 38,
|
100 |
+
"F": 39,
|
101 |
+
"G": 40,
|
102 |
+
"H": 41,
|
103 |
+
"I": 42,
|
104 |
+
"J": 43,
|
105 |
+
"K": 44,
|
106 |
+
"L": 45,
|
107 |
+
"M": 46,
|
108 |
+
"N": 47,
|
109 |
+
"O": 48,
|
110 |
+
"P": 49,
|
111 |
+
"Q": 50,
|
112 |
+
"R": 51,
|
113 |
+
"S": 52,
|
114 |
+
"T": 53,
|
115 |
+
"U": 54,
|
116 |
+
"V": 55,
|
117 |
+
"W": 56,
|
118 |
+
"X": 57,
|
119 |
+
"Y": 58,
|
120 |
+
"Z": 59,
|
121 |
+
"[": 60,
|
122 |
+
"\\": 61,
|
123 |
+
"]": 62,
|
124 |
+
"^": 63,
|
125 |
+
"_": 64,
|
126 |
+
"`": 65,
|
127 |
+
"a": 66,
|
128 |
+
"b": 67,
|
129 |
+
"c": 68,
|
130 |
+
"d": 69,
|
131 |
+
"e": 70,
|
132 |
+
"f": 71,
|
133 |
+
"g": 72,
|
134 |
+
"h": 73,
|
135 |
+
"i": 74,
|
136 |
+
"j": 75,
|
137 |
+
"k": 76,
|
138 |
+
"l": 77,
|
139 |
+
"m": 78,
|
140 |
+
"n": 79,
|
141 |
+
"o": 80,
|
142 |
+
"p": 81,
|
143 |
+
"q": 82,
|
144 |
+
"r": 83,
|
145 |
+
"s": 84,
|
146 |
+
"t": 85,
|
147 |
+
"u": 86,
|
148 |
+
"v": 87,
|
149 |
+
"w": 88,
|
150 |
+
"x": 89,
|
151 |
+
"y": 90,
|
152 |
+
"z": 91,
|
153 |
+
"{": 92,
|
154 |
+
"|": 93,
|
155 |
+
"}": 94,
|
156 |
+
"~": 95,
|
157 |
+
"¡": 96,
|
158 |
+
"¢": 97,
|
159 |
+
"£": 98,
|
160 |
+
"¤": 99,
|
161 |
+
"¥": 100,
|
162 |
+
"¦": 101,
|
163 |
+
"§": 102,
|
164 |
+
"¨": 103,
|
165 |
+
"©": 104,
|
166 |
+
"ª": 105,
|
167 |
+
"«": 106,
|
168 |
+
"¬": 107,
|
169 |
+
"®": 108,
|
170 |
+
"¯": 109,
|
171 |
+
"°": 110,
|
172 |
+
"±": 111,
|
173 |
+
"²": 112,
|
174 |
+
"³": 113,
|
175 |
+
"´": 114,
|
176 |
+
"µ": 115,
|
177 |
+
"¶": 116,
|
178 |
+
"·": 117,
|
179 |
+
"¸": 118,
|
180 |
+
"¹": 119,
|
181 |
+
"º": 120,
|
182 |
+
"»": 121,
|
183 |
+
"¼": 122,
|
184 |
+
"½": 123,
|
185 |
+
"¾": 124,
|
186 |
+
"¿": 125,
|
187 |
+
"À": 126,
|
188 |
+
"Á": 127,
|
189 |
+
"Â": 128,
|
190 |
+
"Ã": 129,
|
191 |
+
"Ä": 130,
|
192 |
+
"Å": 131,
|
193 |
+
"Æ": 132,
|
194 |
+
"Ç": 133,
|
195 |
+
"È": 134,
|
196 |
+
"É": 135,
|
197 |
+
"Ê": 136,
|
198 |
+
"Ë": 137,
|
199 |
+
"Ì": 138,
|
200 |
+
"Í": 139,
|
201 |
+
"Î": 140,
|
202 |
+
"Ï": 141,
|
203 |
+
"Ð": 142,
|
204 |
+
"Ñ": 143,
|
205 |
+
"Ò": 144,
|
206 |
+
"Ó": 145,
|
207 |
+
"Ô": 146,
|
208 |
+
"Õ": 147,
|
209 |
+
"Ö": 148,
|
210 |
+
"×": 149,
|
211 |
+
"Ø": 150,
|
212 |
+
"Ù": 151,
|
213 |
+
"Ú": 152,
|
214 |
+
"Û": 153,
|
215 |
+
"Ü": 154,
|
216 |
+
"Ý": 155,
|
217 |
+
"Þ": 156,
|
218 |
+
"ß": 157,
|
219 |
+
"à": 158,
|
220 |
+
"á": 159,
|
221 |
+
"â": 160,
|
222 |
+
"ã": 161,
|
223 |
+
"ä": 162,
|
224 |
+
"å": 163,
|
225 |
+
"æ": 164,
|
226 |
+
"ç": 165,
|
227 |
+
"è": 166,
|
228 |
+
"é": 167,
|
229 |
+
"ê": 168,
|
230 |
+
"ë": 169,
|
231 |
+
"ì": 170,
|
232 |
+
"í": 171,
|
233 |
+
"î": 172,
|
234 |
+
"ï": 173,
|
235 |
+
"ð": 174,
|
236 |
+
"ñ": 175,
|
237 |
+
"ò": 176,
|
238 |
+
"ó": 177,
|
239 |
+
"ô": 178,
|
240 |
+
"õ": 179,
|
241 |
+
"ö": 180,
|
242 |
+
"÷": 181,
|
243 |
+
"ø": 182,
|
244 |
+
"ù": 183,
|
245 |
+
"ú": 184,
|
246 |
+
"û": 185,
|
247 |
+
"ü": 186,
|
248 |
+
"ý": 187,
|
249 |
+
"þ": 188,
|
250 |
+
"ÿ": 189,
|
251 |
+
"Ā": 190,
|
252 |
+
"ā": 191,
|
253 |
+
"Ă": 192,
|
254 |
+
"ă": 193,
|
255 |
+
"Ą": 194,
|
256 |
+
"ą": 195,
|
257 |
+
"Ć": 196,
|
258 |
+
"ć": 197,
|
259 |
+
"Ĉ": 198,
|
260 |
+
"ĉ": 199,
|
261 |
+
"Ċ": 200,
|
262 |
+
"ċ": 201,
|
263 |
+
"Č": 202,
|
264 |
+
"č": 203,
|
265 |
+
"Ď": 204,
|
266 |
+
"ď": 205,
|
267 |
+
"Đ": 206,
|
268 |
+
"đ": 207,
|
269 |
+
"Ē": 208,
|
270 |
+
"ē": 209,
|
271 |
+
"Ĕ": 210,
|
272 |
+
"ĕ": 211,
|
273 |
+
"Ė": 212,
|
274 |
+
"ė": 213,
|
275 |
+
"Ę": 214,
|
276 |
+
"ę": 215,
|
277 |
+
"Ě": 216,
|
278 |
+
"ě": 217,
|
279 |
+
"Ĝ": 218,
|
280 |
+
"ĝ": 219,
|
281 |
+
"Ğ": 220,
|
282 |
+
"ğ": 221,
|
283 |
+
"Ġ": 222,
|
284 |
+
"ġ": 223,
|
285 |
+
"Ģ": 224,
|
286 |
+
"ģ": 225,
|
287 |
+
"Ĥ": 226,
|
288 |
+
"ĥ": 227,
|
289 |
+
"Ħ": 228,
|
290 |
+
"ħ": 229,
|
291 |
+
"Ĩ": 230,
|
292 |
+
"ĩ": 231,
|
293 |
+
"Ī": 232,
|
294 |
+
"ī": 233,
|
295 |
+
"Ĭ": 234,
|
296 |
+
"ĭ": 235,
|
297 |
+
"Į": 236,
|
298 |
+
"į": 237,
|
299 |
+
"İ": 238,
|
300 |
+
"ı": 239,
|
301 |
+
"IJ": 240,
|
302 |
+
"ij": 241,
|
303 |
+
"Ĵ": 242,
|
304 |
+
"ĵ": 243,
|
305 |
+
"Ķ": 244,
|
306 |
+
"ķ": 245,
|
307 |
+
"ĸ": 246,
|
308 |
+
"Ĺ": 247,
|
309 |
+
"ĺ": 248,
|
310 |
+
"Ļ": 249,
|
311 |
+
"ļ": 250,
|
312 |
+
"Ľ": 251,
|
313 |
+
"ľ": 252,
|
314 |
+
"Ŀ": 253,
|
315 |
+
"ŀ": 254,
|
316 |
+
"Ł": 255,
|
317 |
+
"ł": 256,
|
318 |
+
"Ń": 257,
|
319 |
+
"ng": 258,
|
320 |
+
"er": 259,
|
321 |
+
"ur": 260,
|
322 |
+
"he": 261,
|
323 |
+
"nd": 262,
|
324 |
+
"ss": 263,
|
325 |
+
"gh": 264,
|
326 |
+
"ge": 265,
|
327 |
+
"en": 266,
|
328 |
+
"gr": 267,
|
329 |
+
"up": 268,
|
330 |
+
"ke": 269,
|
331 |
+
"dy": 270,
|
332 |
+
"de": 271,
|
333 |
+
"nt": 272,
|
334 |
+
"rd": 273,
|
335 |
+
"dg": 274,
|
336 |
+
"ve": 275,
|
337 |
+
"rt": 276,
|
338 |
+
"ar": 277,
|
339 |
+
"pl": 278,
|
340 |
+
"in": 279,
|
341 |
+
"ld": 280,
|
342 |
+
"rg": 281,
|
343 |
+
"ly": 282,
|
344 |
+
"ro": 283,
|
345 |
+
"ed": 284,
|
346 |
+
"an": 285,
|
347 |
+
"mb": 286,
|
348 |
+
"te": 287,
|
349 |
+
"nc": 288,
|
350 |
+
"le": 289,
|
351 |
+
"el": 290,
|
352 |
+
"ul": 291,
|
353 |
+
"us": 292,
|
354 |
+
"ym": 293,
|
355 |
+
"qu": 294,
|
356 |
+
"gu": 295,
|
357 |
+
"ll": 296,
|
358 |
+
"wn": 297,
|
359 |
+
"rk": 298,
|
360 |
+
"her": 299,
|
361 |
+
"um": 300,
|
362 |
+
"ig": 301,
|
363 |
+
"es": 302,
|
364 |
+
"ce": 303,
|
365 |
+
"em": 304,
|
366 |
+
"ib": 305,
|
367 |
+
"tr": 306,
|
368 |
+
"on": 307,
|
369 |
+
"cl": 308,
|
370 |
+
"ma": 309,
|
371 |
+
"se": 310,
|
372 |
+
"li": 311,
|
373 |
+
"me": 312,
|
374 |
+
"th": 313,
|
375 |
+
"bl": 314,
|
376 |
+
"den": 315,
|
377 |
+
"gn": 316,
|
378 |
+
"ow": 317,
|
379 |
+
"rc": 318,
|
380 |
+
"at": 319,
|
381 |
+
"et": 320,
|
382 |
+
"ch": 321,
|
383 |
+
"du": 322,
|
384 |
+
"ud": 323,
|
385 |
+
"al": 324,
|
386 |
+
"uc": 325,
|
387 |
+
"ug": 326,
|
388 |
+
"iv": 327,
|
389 |
+
"bu": 328,
|
390 |
+
"and": 329,
|
391 |
+
"ut": 330,
|
392 |
+
"sh": 331,
|
393 |
+
"la": 332,
|
394 |
+
"ec": 333,
|
395 |
+
"io": 334,
|
396 |
+
"ard": 335,
|
397 |
+
"ra": 336,
|
398 |
+
"om": 337,
|
399 |
+
"ou": 338,
|
400 |
+
"og": 339,
|
401 |
+
"ct": 340,
|
402 |
+
"oup": 341,
|
403 |
+
"vi": 342,
|
404 |
+
"dro": 343,
|
405 |
+
"ti": 344,
|
406 |
+
"ent": 345,
|
407 |
+
"ck": 346,
|
408 |
+
"ple": 347,
|
409 |
+
"ue": 348,
|
410 |
+
"ing": 349,
|
411 |
+
"mal": 350,
|
412 |
+
"or": 351,
|
413 |
+
"po": 352,
|
414 |
+
"re": 353,
|
415 |
+
"lt": 354,
|
416 |
+
"rn": 355,
|
417 |
+
"st": 356,
|
418 |
+
"od": 357,
|
419 |
+
"rm": 358,
|
420 |
+
"ag": 359,
|
421 |
+
"sk": 360,
|
422 |
+
"ea": 361,
|
423 |
+
"to": 362,
|
424 |
+
"il": 363,
|
425 |
+
"bi": 364,
|
426 |
+
"the": 365,
|
427 |
+
"ey": 366,
|
428 |
+
"und": 367,
|
429 |
+
"ia": 368,
|
430 |
+
"hi": 369,
|
431 |
+
"ri": 370,
|
432 |
+
"ugh": 371,
|
433 |
+
"am": 372,
|
434 |
+
"ca": 373,
|
435 |
+
"get": 374,
|
436 |
+
"it": 375,
|
437 |
+
"ic": 376,
|
438 |
+
"ak": 377,
|
439 |
+
"ht": 378,
|
440 |
+
"rv": 379,
|
441 |
+
"but": 380,
|
442 |
+
"ay": 381,
|
443 |
+
"na": 382,
|
444 |
+
"as": 383,
|
445 |
+
"ad": 384,
|
446 |
+
"nce": 385,
|
447 |
+
"un": 386,
|
448 |
+
"ns": 387,
|
449 |
+
"su": 388,
|
450 |
+
"ir": 389,
|
451 |
+
"ty": 390,
|
452 |
+
"ov": 391,
|
453 |
+
"tu": 392,
|
454 |
+
"oy": 393,
|
455 |
+
"ap": 394,
|
456 |
+
"gd": 395,
|
457 |
+
"ip": 396,
|
458 |
+
"rom": 397,
|
459 |
+
"tur": 398,
|
460 |
+
"ect": 399,
|
461 |
+
"ff": 400,
|
462 |
+
"ion": 401,
|
463 |
+
"im": 402,
|
464 |
+
"lo": 403,
|
465 |
+
"pt": 404,
|
466 |
+
"use": 405,
|
467 |
+
"ui": 406,
|
468 |
+
"ish": 407,
|
469 |
+
"ne": 408,
|
470 |
+
"di": 409,
|
471 |
+
"av": 410,
|
472 |
+
"ga": 411,
|
473 |
+
"no": 412,
|
474 |
+
"op": 413,
|
475 |
+
"ger": 414,
|
476 |
+
"is": 415,
|
477 |
+
"drom": 416,
|
478 |
+
"ie": 417,
|
479 |
+
"we": 418,
|
480 |
+
"ph": 419,
|
481 |
+
"da": 420,
|
482 |
+
"rr": 421,
|
483 |
+
"mat": 422,
|
484 |
+
"mo": 423,
|
485 |
+
"be": 424,
|
486 |
+
"ai": 425,
|
487 |
+
"id": 426,
|
488 |
+
"lly": 427,
|
489 |
+
"gra": 428,
|
490 |
+
"ure": 429,
|
491 |
+
"ler": 430,
|
492 |
+
"ac": 431,
|
493 |
+
"ha": 432,
|
494 |
+
"der": 433,
|
495 |
+
"do": 434,
|
496 |
+
"nk": 435,
|
497 |
+
"age": 436,
|
498 |
+
"si": 437,
|
499 |
+
"mp": 438,
|
500 |
+
"dl": 439,
|
501 |
+
"igh": 440,
|
502 |
+
"ba": 441,
|
503 |
+
"ol": 442,
|
504 |
+
"ua": 443,
|
505 |
+
"ab": 444,
|
506 |
+
"ther": 445,
|
507 |
+
"ess": 446,
|
508 |
+
"rde": 447,
|
509 |
+
"vel": 448,
|
510 |
+
"ni": 449,
|
511 |
+
"tem": 450,
|
512 |
+
"rch": 451,
|
513 |
+
"lem": 452,
|
514 |
+
"ci": 453,
|
515 |
+
"mu": 454,
|
516 |
+
"ber": 455,
|
517 |
+
"men": 456,
|
518 |
+
"os": 457,
|
519 |
+
"mn": 458,
|
520 |
+
"ko": 459,
|
521 |
+
"ase": 460,
|
522 |
+
"ver": 461,
|
523 |
+
"oo": 462,
|
524 |
+
"dr": 463,
|
525 |
+
"ide": 464,
|
526 |
+
"rap": 465,
|
527 |
+
"ate": 466,
|
528 |
+
"est": 467,
|
529 |
+
"rty": 468,
|
530 |
+
"va": 469,
|
531 |
+
"cu": 470,
|
532 |
+
"ee": 471,
|
533 |
+
"pe": 472,
|
534 |
+
"lf": 473,
|
535 |
+
"ft": 474,
|
536 |
+
"ho": 475,
|
537 |
+
"tt": 476,
|
538 |
+
"ta": 477,
|
539 |
+
"eg": 478,
|
540 |
+
"icl": 479,
|
541 |
+
"lio": 480,
|
542 |
+
"mi": 481,
|
543 |
+
"cer": 482,
|
544 |
+
"yl": 483,
|
545 |
+
"ok": 484,
|
546 |
+
"ork": 485,
|
547 |
+
"ka": 486,
|
548 |
+
"fe": 487,
|
549 |
+
"ry": 488,
|
550 |
+
"ult": 489,
|
551 |
+
"ltur": 490,
|
552 |
+
"lu": 491,
|
553 |
+
"ram": 492,
|
554 |
+
"ethe": 493,
|
555 |
+
"ev": 494,
|
556 |
+
"nat": 495,
|
557 |
+
"rs": 496,
|
558 |
+
"tl": 497,
|
559 |
+
"ght": 498,
|
560 |
+
"tion": 499
|
561 |
+
},
|
562 |
+
"merges": [
|
563 |
+
[
|
564 |
+
"n",
|
565 |
+
"g"
|
566 |
+
],
|
567 |
+
[
|
568 |
+
"e",
|
569 |
+
"r"
|
570 |
+
],
|
571 |
+
[
|
572 |
+
"u",
|
573 |
+
"r"
|
574 |
+
],
|
575 |
+
[
|
576 |
+
"h",
|
577 |
+
"e"
|
578 |
+
],
|
579 |
+
[
|
580 |
+
"n",
|
581 |
+
"d"
|
582 |
+
],
|
583 |
+
[
|
584 |
+
"s",
|
585 |
+
"s"
|
586 |
+
],
|
587 |
+
[
|
588 |
+
"g",
|
589 |
+
"h"
|
590 |
+
],
|
591 |
+
[
|
592 |
+
"g",
|
593 |
+
"e"
|
594 |
+
],
|
595 |
+
[
|
596 |
+
"e",
|
597 |
+
"n"
|
598 |
+
],
|
599 |
+
[
|
600 |
+
"g",
|
601 |
+
"r"
|
602 |
+
],
|
603 |
+
[
|
604 |
+
"u",
|
605 |
+
"p"
|
606 |
+
],
|
607 |
+
[
|
608 |
+
"k",
|
609 |
+
"e"
|
610 |
+
],
|
611 |
+
[
|
612 |
+
"d",
|
613 |
+
"y"
|
614 |
+
],
|
615 |
+
[
|
616 |
+
"d",
|
617 |
+
"e"
|
618 |
+
],
|
619 |
+
[
|
620 |
+
"n",
|
621 |
+
"t"
|
622 |
+
],
|
623 |
+
[
|
624 |
+
"r",
|
625 |
+
"d"
|
626 |
+
],
|
627 |
+
[
|
628 |
+
"d",
|
629 |
+
"g"
|
630 |
+
],
|
631 |
+
[
|
632 |
+
"v",
|
633 |
+
"e"
|
634 |
+
],
|
635 |
+
[
|
636 |
+
"r",
|
637 |
+
"t"
|
638 |
+
],
|
639 |
+
[
|
640 |
+
"a",
|
641 |
+
"r"
|
642 |
+
],
|
643 |
+
[
|
644 |
+
"p",
|
645 |
+
"l"
|
646 |
+
],
|
647 |
+
[
|
648 |
+
"i",
|
649 |
+
"n"
|
650 |
+
],
|
651 |
+
[
|
652 |
+
"l",
|
653 |
+
"d"
|
654 |
+
],
|
655 |
+
[
|
656 |
+
"r",
|
657 |
+
"g"
|
658 |
+
],
|
659 |
+
[
|
660 |
+
"l",
|
661 |
+
"y"
|
662 |
+
],
|
663 |
+
[
|
664 |
+
"r",
|
665 |
+
"o"
|
666 |
+
],
|
667 |
+
[
|
668 |
+
"e",
|
669 |
+
"d"
|
670 |
+
],
|
671 |
+
[
|
672 |
+
"a",
|
673 |
+
"n"
|
674 |
+
],
|
675 |
+
[
|
676 |
+
"m",
|
677 |
+
"b"
|
678 |
+
],
|
679 |
+
[
|
680 |
+
"t",
|
681 |
+
"e"
|
682 |
+
],
|
683 |
+
[
|
684 |
+
"n",
|
685 |
+
"c"
|
686 |
+
],
|
687 |
+
[
|
688 |
+
"l",
|
689 |
+
"e"
|
690 |
+
],
|
691 |
+
[
|
692 |
+
"e",
|
693 |
+
"l"
|
694 |
+
],
|
695 |
+
[
|
696 |
+
"u",
|
697 |
+
"l"
|
698 |
+
],
|
699 |
+
[
|
700 |
+
"u",
|
701 |
+
"s"
|
702 |
+
],
|
703 |
+
[
|
704 |
+
"y",
|
705 |
+
"m"
|
706 |
+
],
|
707 |
+
[
|
708 |
+
"q",
|
709 |
+
"u"
|
710 |
+
],
|
711 |
+
[
|
712 |
+
"g",
|
713 |
+
"u"
|
714 |
+
],
|
715 |
+
[
|
716 |
+
"l",
|
717 |
+
"l"
|
718 |
+
],
|
719 |
+
[
|
720 |
+
"w",
|
721 |
+
"n"
|
722 |
+
],
|
723 |
+
[
|
724 |
+
"r",
|
725 |
+
"k"
|
726 |
+
],
|
727 |
+
[
|
728 |
+
"h",
|
729 |
+
"er"
|
730 |
+
],
|
731 |
+
[
|
732 |
+
"u",
|
733 |
+
"m"
|
734 |
+
],
|
735 |
+
[
|
736 |
+
"i",
|
737 |
+
"g"
|
738 |
+
],
|
739 |
+
[
|
740 |
+
"e",
|
741 |
+
"s"
|
742 |
+
],
|
743 |
+
[
|
744 |
+
"c",
|
745 |
+
"e"
|
746 |
+
],
|
747 |
+
[
|
748 |
+
"e",
|
749 |
+
"m"
|
750 |
+
],
|
751 |
+
[
|
752 |
+
"i",
|
753 |
+
"b"
|
754 |
+
],
|
755 |
+
[
|
756 |
+
"t",
|
757 |
+
"r"
|
758 |
+
],
|
759 |
+
[
|
760 |
+
"o",
|
761 |
+
"n"
|
762 |
+
],
|
763 |
+
[
|
764 |
+
"c",
|
765 |
+
"l"
|
766 |
+
],
|
767 |
+
[
|
768 |
+
"m",
|
769 |
+
"a"
|
770 |
+
],
|
771 |
+
[
|
772 |
+
"s",
|
773 |
+
"e"
|
774 |
+
],
|
775 |
+
[
|
776 |
+
"l",
|
777 |
+
"i"
|
778 |
+
],
|
779 |
+
[
|
780 |
+
"m",
|
781 |
+
"e"
|
782 |
+
],
|
783 |
+
[
|
784 |
+
"t",
|
785 |
+
"h"
|
786 |
+
],
|
787 |
+
[
|
788 |
+
"b",
|
789 |
+
"l"
|
790 |
+
],
|
791 |
+
[
|
792 |
+
"d",
|
793 |
+
"en"
|
794 |
+
],
|
795 |
+
[
|
796 |
+
"g",
|
797 |
+
"n"
|
798 |
+
],
|
799 |
+
[
|
800 |
+
"o",
|
801 |
+
"w"
|
802 |
+
],
|
803 |
+
[
|
804 |
+
"r",
|
805 |
+
"c"
|
806 |
+
],
|
807 |
+
[
|
808 |
+
"a",
|
809 |
+
"t"
|
810 |
+
],
|
811 |
+
[
|
812 |
+
"e",
|
813 |
+
"t"
|
814 |
+
],
|
815 |
+
[
|
816 |
+
"c",
|
817 |
+
"h"
|
818 |
+
],
|
819 |
+
[
|
820 |
+
"d",
|
821 |
+
"u"
|
822 |
+
],
|
823 |
+
[
|
824 |
+
"u",
|
825 |
+
"d"
|
826 |
+
],
|
827 |
+
[
|
828 |
+
"a",
|
829 |
+
"l"
|
830 |
+
],
|
831 |
+
[
|
832 |
+
"u",
|
833 |
+
"c"
|
834 |
+
],
|
835 |
+
[
|
836 |
+
"u",
|
837 |
+
"g"
|
838 |
+
],
|
839 |
+
[
|
840 |
+
"i",
|
841 |
+
"v"
|
842 |
+
],
|
843 |
+
[
|
844 |
+
"b",
|
845 |
+
"u"
|
846 |
+
],
|
847 |
+
[
|
848 |
+
"a",
|
849 |
+
"nd"
|
850 |
+
],
|
851 |
+
[
|
852 |
+
"u",
|
853 |
+
"t"
|
854 |
+
],
|
855 |
+
[
|
856 |
+
"s",
|
857 |
+
"h"
|
858 |
+
],
|
859 |
+
[
|
860 |
+
"l",
|
861 |
+
"a"
|
862 |
+
],
|
863 |
+
[
|
864 |
+
"e",
|
865 |
+
"c"
|
866 |
+
],
|
867 |
+
[
|
868 |
+
"i",
|
869 |
+
"o"
|
870 |
+
],
|
871 |
+
[
|
872 |
+
"a",
|
873 |
+
"rd"
|
874 |
+
],
|
875 |
+
[
|
876 |
+
"r",
|
877 |
+
"a"
|
878 |
+
],
|
879 |
+
[
|
880 |
+
"o",
|
881 |
+
"m"
|
882 |
+
],
|
883 |
+
[
|
884 |
+
"o",
|
885 |
+
"u"
|
886 |
+
],
|
887 |
+
[
|
888 |
+
"o",
|
889 |
+
"g"
|
890 |
+
],
|
891 |
+
[
|
892 |
+
"c",
|
893 |
+
"t"
|
894 |
+
],
|
895 |
+
[
|
896 |
+
"o",
|
897 |
+
"up"
|
898 |
+
],
|
899 |
+
[
|
900 |
+
"v",
|
901 |
+
"i"
|
902 |
+
],
|
903 |
+
[
|
904 |
+
"d",
|
905 |
+
"ro"
|
906 |
+
],
|
907 |
+
[
|
908 |
+
"t",
|
909 |
+
"i"
|
910 |
+
],
|
911 |
+
[
|
912 |
+
"e",
|
913 |
+
"nt"
|
914 |
+
],
|
915 |
+
[
|
916 |
+
"c",
|
917 |
+
"k"
|
918 |
+
],
|
919 |
+
[
|
920 |
+
"pl",
|
921 |
+
"e"
|
922 |
+
],
|
923 |
+
[
|
924 |
+
"u",
|
925 |
+
"e"
|
926 |
+
],
|
927 |
+
[
|
928 |
+
"i",
|
929 |
+
"ng"
|
930 |
+
],
|
931 |
+
[
|
932 |
+
"ma",
|
933 |
+
"l"
|
934 |
+
],
|
935 |
+
[
|
936 |
+
"o",
|
937 |
+
"r"
|
938 |
+
],
|
939 |
+
[
|
940 |
+
"p",
|
941 |
+
"o"
|
942 |
+
],
|
943 |
+
[
|
944 |
+
"r",
|
945 |
+
"e"
|
946 |
+
],
|
947 |
+
[
|
948 |
+
"l",
|
949 |
+
"t"
|
950 |
+
],
|
951 |
+
[
|
952 |
+
"r",
|
953 |
+
"n"
|
954 |
+
],
|
955 |
+
[
|
956 |
+
"s",
|
957 |
+
"t"
|
958 |
+
],
|
959 |
+
[
|
960 |
+
"o",
|
961 |
+
"d"
|
962 |
+
],
|
963 |
+
[
|
964 |
+
"r",
|
965 |
+
"m"
|
966 |
+
],
|
967 |
+
[
|
968 |
+
"a",
|
969 |
+
"g"
|
970 |
+
],
|
971 |
+
[
|
972 |
+
"s",
|
973 |
+
"k"
|
974 |
+
],
|
975 |
+
[
|
976 |
+
"e",
|
977 |
+
"a"
|
978 |
+
],
|
979 |
+
[
|
980 |
+
"t",
|
981 |
+
"o"
|
982 |
+
],
|
983 |
+
[
|
984 |
+
"i",
|
985 |
+
"l"
|
986 |
+
],
|
987 |
+
[
|
988 |
+
"b",
|
989 |
+
"i"
|
990 |
+
],
|
991 |
+
[
|
992 |
+
"th",
|
993 |
+
"e"
|
994 |
+
],
|
995 |
+
[
|
996 |
+
"e",
|
997 |
+
"y"
|
998 |
+
],
|
999 |
+
[
|
1000 |
+
"u",
|
1001 |
+
"nd"
|
1002 |
+
],
|
1003 |
+
[
|
1004 |
+
"i",
|
1005 |
+
"a"
|
1006 |
+
],
|
1007 |
+
[
|
1008 |
+
"h",
|
1009 |
+
"i"
|
1010 |
+
],
|
1011 |
+
[
|
1012 |
+
"r",
|
1013 |
+
"i"
|
1014 |
+
],
|
1015 |
+
[
|
1016 |
+
"ug",
|
1017 |
+
"h"
|
1018 |
+
],
|
1019 |
+
[
|
1020 |
+
"a",
|
1021 |
+
"m"
|
1022 |
+
],
|
1023 |
+
[
|
1024 |
+
"c",
|
1025 |
+
"a"
|
1026 |
+
],
|
1027 |
+
[
|
1028 |
+
"g",
|
1029 |
+
"et"
|
1030 |
+
],
|
1031 |
+
[
|
1032 |
+
"i",
|
1033 |
+
"t"
|
1034 |
+
],
|
1035 |
+
[
|
1036 |
+
"i",
|
1037 |
+
"c"
|
1038 |
+
],
|
1039 |
+
[
|
1040 |
+
"a",
|
1041 |
+
"k"
|
1042 |
+
],
|
1043 |
+
[
|
1044 |
+
"h",
|
1045 |
+
"t"
|
1046 |
+
],
|
1047 |
+
[
|
1048 |
+
"r",
|
1049 |
+
"v"
|
1050 |
+
],
|
1051 |
+
[
|
1052 |
+
"b",
|
1053 |
+
"ut"
|
1054 |
+
],
|
1055 |
+
[
|
1056 |
+
"a",
|
1057 |
+
"y"
|
1058 |
+
],
|
1059 |
+
[
|
1060 |
+
"n",
|
1061 |
+
"a"
|
1062 |
+
],
|
1063 |
+
[
|
1064 |
+
"a",
|
1065 |
+
"s"
|
1066 |
+
],
|
1067 |
+
[
|
1068 |
+
"a",
|
1069 |
+
"d"
|
1070 |
+
],
|
1071 |
+
[
|
1072 |
+
"n",
|
1073 |
+
"ce"
|
1074 |
+
],
|
1075 |
+
[
|
1076 |
+
"u",
|
1077 |
+
"n"
|
1078 |
+
],
|
1079 |
+
[
|
1080 |
+
"n",
|
1081 |
+
"s"
|
1082 |
+
],
|
1083 |
+
[
|
1084 |
+
"s",
|
1085 |
+
"u"
|
1086 |
+
],
|
1087 |
+
[
|
1088 |
+
"i",
|
1089 |
+
"r"
|
1090 |
+
],
|
1091 |
+
[
|
1092 |
+
"t",
|
1093 |
+
"y"
|
1094 |
+
],
|
1095 |
+
[
|
1096 |
+
"o",
|
1097 |
+
"v"
|
1098 |
+
],
|
1099 |
+
[
|
1100 |
+
"t",
|
1101 |
+
"u"
|
1102 |
+
],
|
1103 |
+
[
|
1104 |
+
"o",
|
1105 |
+
"y"
|
1106 |
+
],
|
1107 |
+
[
|
1108 |
+
"a",
|
1109 |
+
"p"
|
1110 |
+
],
|
1111 |
+
[
|
1112 |
+
"g",
|
1113 |
+
"d"
|
1114 |
+
],
|
1115 |
+
[
|
1116 |
+
"i",
|
1117 |
+
"p"
|
1118 |
+
],
|
1119 |
+
[
|
1120 |
+
"ro",
|
1121 |
+
"m"
|
1122 |
+
],
|
1123 |
+
[
|
1124 |
+
"t",
|
1125 |
+
"ur"
|
1126 |
+
],
|
1127 |
+
[
|
1128 |
+
"ec",
|
1129 |
+
"t"
|
1130 |
+
],
|
1131 |
+
[
|
1132 |
+
"f",
|
1133 |
+
"f"
|
1134 |
+
],
|
1135 |
+
[
|
1136 |
+
"i",
|
1137 |
+
"on"
|
1138 |
+
],
|
1139 |
+
[
|
1140 |
+
"i",
|
1141 |
+
"m"
|
1142 |
+
],
|
1143 |
+
[
|
1144 |
+
"l",
|
1145 |
+
"o"
|
1146 |
+
],
|
1147 |
+
[
|
1148 |
+
"p",
|
1149 |
+
"t"
|
1150 |
+
],
|
1151 |
+
[
|
1152 |
+
"u",
|
1153 |
+
"se"
|
1154 |
+
],
|
1155 |
+
[
|
1156 |
+
"u",
|
1157 |
+
"i"
|
1158 |
+
],
|
1159 |
+
[
|
1160 |
+
"i",
|
1161 |
+
"sh"
|
1162 |
+
],
|
1163 |
+
[
|
1164 |
+
"n",
|
1165 |
+
"e"
|
1166 |
+
],
|
1167 |
+
[
|
1168 |
+
"d",
|
1169 |
+
"i"
|
1170 |
+
],
|
1171 |
+
[
|
1172 |
+
"a",
|
1173 |
+
"v"
|
1174 |
+
],
|
1175 |
+
[
|
1176 |
+
"g",
|
1177 |
+
"a"
|
1178 |
+
],
|
1179 |
+
[
|
1180 |
+
"n",
|
1181 |
+
"o"
|
1182 |
+
],
|
1183 |
+
[
|
1184 |
+
"o",
|
1185 |
+
"p"
|
1186 |
+
],
|
1187 |
+
[
|
1188 |
+
"ge",
|
1189 |
+
"r"
|
1190 |
+
],
|
1191 |
+
[
|
1192 |
+
"i",
|
1193 |
+
"s"
|
1194 |
+
],
|
1195 |
+
[
|
1196 |
+
"d",
|
1197 |
+
"rom"
|
1198 |
+
],
|
1199 |
+
[
|
1200 |
+
"i",
|
1201 |
+
"e"
|
1202 |
+
],
|
1203 |
+
[
|
1204 |
+
"w",
|
1205 |
+
"e"
|
1206 |
+
],
|
1207 |
+
[
|
1208 |
+
"p",
|
1209 |
+
"h"
|
1210 |
+
],
|
1211 |
+
[
|
1212 |
+
"d",
|
1213 |
+
"a"
|
1214 |
+
],
|
1215 |
+
[
|
1216 |
+
"r",
|
1217 |
+
"r"
|
1218 |
+
],
|
1219 |
+
[
|
1220 |
+
"m",
|
1221 |
+
"at"
|
1222 |
+
],
|
1223 |
+
[
|
1224 |
+
"m",
|
1225 |
+
"o"
|
1226 |
+
],
|
1227 |
+
[
|
1228 |
+
"b",
|
1229 |
+
"e"
|
1230 |
+
],
|
1231 |
+
[
|
1232 |
+
"a",
|
1233 |
+
"i"
|
1234 |
+
],
|
1235 |
+
[
|
1236 |
+
"i",
|
1237 |
+
"d"
|
1238 |
+
],
|
1239 |
+
[
|
1240 |
+
"ll",
|
1241 |
+
"y"
|
1242 |
+
],
|
1243 |
+
[
|
1244 |
+
"gr",
|
1245 |
+
"a"
|
1246 |
+
],
|
1247 |
+
[
|
1248 |
+
"u",
|
1249 |
+
"re"
|
1250 |
+
],
|
1251 |
+
[
|
1252 |
+
"l",
|
1253 |
+
"er"
|
1254 |
+
],
|
1255 |
+
[
|
1256 |
+
"a",
|
1257 |
+
"c"
|
1258 |
+
],
|
1259 |
+
[
|
1260 |
+
"h",
|
1261 |
+
"a"
|
1262 |
+
],
|
1263 |
+
[
|
1264 |
+
"d",
|
1265 |
+
"er"
|
1266 |
+
],
|
1267 |
+
[
|
1268 |
+
"d",
|
1269 |
+
"o"
|
1270 |
+
],
|
1271 |
+
[
|
1272 |
+
"n",
|
1273 |
+
"k"
|
1274 |
+
],
|
1275 |
+
[
|
1276 |
+
"ag",
|
1277 |
+
"e"
|
1278 |
+
],
|
1279 |
+
[
|
1280 |
+
"s",
|
1281 |
+
"i"
|
1282 |
+
],
|
1283 |
+
[
|
1284 |
+
"m",
|
1285 |
+
"p"
|
1286 |
+
],
|
1287 |
+
[
|
1288 |
+
"d",
|
1289 |
+
"l"
|
1290 |
+
],
|
1291 |
+
[
|
1292 |
+
"ig",
|
1293 |
+
"h"
|
1294 |
+
],
|
1295 |
+
[
|
1296 |
+
"b",
|
1297 |
+
"a"
|
1298 |
+
],
|
1299 |
+
[
|
1300 |
+
"o",
|
1301 |
+
"l"
|
1302 |
+
],
|
1303 |
+
[
|
1304 |
+
"u",
|
1305 |
+
"a"
|
1306 |
+
],
|
1307 |
+
[
|
1308 |
+
"a",
|
1309 |
+
"b"
|
1310 |
+
],
|
1311 |
+
[
|
1312 |
+
"the",
|
1313 |
+
"r"
|
1314 |
+
],
|
1315 |
+
[
|
1316 |
+
"e",
|
1317 |
+
"ss"
|
1318 |
+
],
|
1319 |
+
[
|
1320 |
+
"rd",
|
1321 |
+
"e"
|
1322 |
+
],
|
1323 |
+
[
|
1324 |
+
"ve",
|
1325 |
+
"l"
|
1326 |
+
],
|
1327 |
+
[
|
1328 |
+
"n",
|
1329 |
+
"i"
|
1330 |
+
],
|
1331 |
+
[
|
1332 |
+
"t",
|
1333 |
+
"em"
|
1334 |
+
],
|
1335 |
+
[
|
1336 |
+
"r",
|
1337 |
+
"ch"
|
1338 |
+
],
|
1339 |
+
[
|
1340 |
+
"l",
|
1341 |
+
"em"
|
1342 |
+
],
|
1343 |
+
[
|
1344 |
+
"c",
|
1345 |
+
"i"
|
1346 |
+
],
|
1347 |
+
[
|
1348 |
+
"m",
|
1349 |
+
"u"
|
1350 |
+
],
|
1351 |
+
[
|
1352 |
+
"b",
|
1353 |
+
"er"
|
1354 |
+
],
|
1355 |
+
[
|
1356 |
+
"m",
|
1357 |
+
"en"
|
1358 |
+
],
|
1359 |
+
[
|
1360 |
+
"o",
|
1361 |
+
"s"
|
1362 |
+
],
|
1363 |
+
[
|
1364 |
+
"m",
|
1365 |
+
"n"
|
1366 |
+
],
|
1367 |
+
[
|
1368 |
+
"k",
|
1369 |
+
"o"
|
1370 |
+
],
|
1371 |
+
[
|
1372 |
+
"a",
|
1373 |
+
"se"
|
1374 |
+
],
|
1375 |
+
[
|
1376 |
+
"ve",
|
1377 |
+
"r"
|
1378 |
+
],
|
1379 |
+
[
|
1380 |
+
"o",
|
1381 |
+
"o"
|
1382 |
+
],
|
1383 |
+
[
|
1384 |
+
"d",
|
1385 |
+
"r"
|
1386 |
+
],
|
1387 |
+
[
|
1388 |
+
"i",
|
1389 |
+
"de"
|
1390 |
+
],
|
1391 |
+
[
|
1392 |
+
"r",
|
1393 |
+
"ap"
|
1394 |
+
],
|
1395 |
+
[
|
1396 |
+
"a",
|
1397 |
+
"te"
|
1398 |
+
],
|
1399 |
+
[
|
1400 |
+
"e",
|
1401 |
+
"st"
|
1402 |
+
],
|
1403 |
+
[
|
1404 |
+
"r",
|
1405 |
+
"ty"
|
1406 |
+
],
|
1407 |
+
[
|
1408 |
+
"v",
|
1409 |
+
"a"
|
1410 |
+
],
|
1411 |
+
[
|
1412 |
+
"c",
|
1413 |
+
"u"
|
1414 |
+
],
|
1415 |
+
[
|
1416 |
+
"e",
|
1417 |
+
"e"
|
1418 |
+
],
|
1419 |
+
[
|
1420 |
+
"p",
|
1421 |
+
"e"
|
1422 |
+
],
|
1423 |
+
[
|
1424 |
+
"l",
|
1425 |
+
"f"
|
1426 |
+
],
|
1427 |
+
[
|
1428 |
+
"f",
|
1429 |
+
"t"
|
1430 |
+
],
|
1431 |
+
[
|
1432 |
+
"h",
|
1433 |
+
"o"
|
1434 |
+
],
|
1435 |
+
[
|
1436 |
+
"t",
|
1437 |
+
"t"
|
1438 |
+
],
|
1439 |
+
[
|
1440 |
+
"t",
|
1441 |
+
"a"
|
1442 |
+
],
|
1443 |
+
[
|
1444 |
+
"e",
|
1445 |
+
"g"
|
1446 |
+
],
|
1447 |
+
[
|
1448 |
+
"i",
|
1449 |
+
"cl"
|
1450 |
+
],
|
1451 |
+
[
|
1452 |
+
"l",
|
1453 |
+
"io"
|
1454 |
+
],
|
1455 |
+
[
|
1456 |
+
"m",
|
1457 |
+
"i"
|
1458 |
+
],
|
1459 |
+
[
|
1460 |
+
"c",
|
1461 |
+
"er"
|
1462 |
+
],
|
1463 |
+
[
|
1464 |
+
"y",
|
1465 |
+
"l"
|
1466 |
+
],
|
1467 |
+
[
|
1468 |
+
"o",
|
1469 |
+
"k"
|
1470 |
+
],
|
1471 |
+
[
|
1472 |
+
"o",
|
1473 |
+
"rk"
|
1474 |
+
],
|
1475 |
+
[
|
1476 |
+
"k",
|
1477 |
+
"a"
|
1478 |
+
],
|
1479 |
+
[
|
1480 |
+
"f",
|
1481 |
+
"e"
|
1482 |
+
],
|
1483 |
+
[
|
1484 |
+
"r",
|
1485 |
+
"y"
|
1486 |
+
],
|
1487 |
+
[
|
1488 |
+
"ul",
|
1489 |
+
"t"
|
1490 |
+
],
|
1491 |
+
[
|
1492 |
+
"l",
|
1493 |
+
"tur"
|
1494 |
+
],
|
1495 |
+
[
|
1496 |
+
"l",
|
1497 |
+
"u"
|
1498 |
+
],
|
1499 |
+
[
|
1500 |
+
"r",
|
1501 |
+
"am"
|
1502 |
+
],
|
1503 |
+
[
|
1504 |
+
"e",
|
1505 |
+
"the"
|
1506 |
+
],
|
1507 |
+
[
|
1508 |
+
"e",
|
1509 |
+
"v"
|
1510 |
+
],
|
1511 |
+
[
|
1512 |
+
"n",
|
1513 |
+
"at"
|
1514 |
+
],
|
1515 |
+
[
|
1516 |
+
"r",
|
1517 |
+
"s"
|
1518 |
+
],
|
1519 |
+
[
|
1520 |
+
"t",
|
1521 |
+
"l"
|
1522 |
+
],
|
1523 |
+
[
|
1524 |
+
"gh",
|
1525 |
+
"t"
|
1526 |
+
],
|
1527 |
+
[
|
1528 |
+
"t",
|
1529 |
+
"ion"
|
1530 |
+
]
|
1531 |
+
]
|
1532 |
+
}
|
1533 |
+
}
|
fw57M_Entropy_thresholdM_500/tokenizer_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|padding|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|endoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": false,
|
23 |
+
"eos_token": "<|endoftext|>",
|
24 |
+
"extra_special_tokens": {},
|
25 |
+
"model_max_length": 1000000000000000019884624838656,
|
26 |
+
"pad_token": "<|padding|>",
|
27 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
28 |
+
"unk_token": null
|
29 |
+
}
|
fw57M_Entropy_thresholdM_500/vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"g": 72, "\u012b": 233, "c": 68, "\u00e3": 161, "O": 48, "\u00bd": 123, "\u00a4": 99, "\u0133": 241, "\u011f": 221, "!": 2, "0": 17, "\u00c9": 135, "\u010a": 200, "\u0131": 239, "`": 65, "\u00a5": 100, "C": 36, "\u00c1": 127, "j": 75, "#": 4, "\u00c4": 130, "\u0130": 238, "\u0120": 222, "\u00b4": 114, "\u00d5": 147, "\u00f4": 178, "\u00dc": 154, "\u00e1": 159, "\u00a2": 97, "H": 41, "d": 69, "%": 6, "Y": 58, "\u0107": 197, "\u0119": 215, "\u011c": 218, "\u00db": 153, "\u0129": 231, "\u013e": 252, "\u00b5": 115, "\u00d6": 148, "\u00f2": 176, "\u00fd": 187, "\u00fe": 188, "\u011d": 219, "\u00b3": 113, "\u0142": 256, "5": 22, "T": 53, "\u00d9": 151, "\u0113": 209, "\u00a1": 96, "\u0135": 243, "a": 66, "<|padding|>": 0, "8": 25, "|": 93, "S": 52, "\u00ba": 120, "W": 56, "\u0139": 247, "\u0140": 254, "X": 57, "E": 38, "\u00dd": 155, "\u00ab": 106, "\u00d8": 150, "\u0100": 190, ":": 27, "K": 44, "\u00a3": 98, "f": 71, "}": 94, "U": 54, "\u0105": 195, "\u00aa": 105, "h": 73, "\u013a": 248, "\u00be": 124, "\u00c5": 131, "P": 49, "s": 84, "\u0125": 227, "9": 26, "{": 92, "*": 11, "-": 14, "N": 47, "$": 5, "\u00ce": 140, "A": 34, "\u00f7": 181, "\u00fc": 186, "<": 29, "\u0132": 240, "V": 55, "(": 9, "L": 45, "l": 77, "\u00d1": 143, "r": 83, "\u00ef": 173, "G": 40, "\u00d7": 149, "J": 43, "\u0137": 245, "@": 33, "R": 51, "\u00f9": 183, "B": 35, "\u00bc": 122, "7": 24, "\u00ac": 107, "\u00e9": 167, "\u00b0": 110, "n": 79, "u": 86, "~": 95, "\u00f5": 179, "\u011a": 216, "\u011b": 217, "\u0134": 242, "\u0114": 210, "\u00a7": 102, "\u00f3": 177, "\u00eb": 169, "\u012f": 237, "y": 90, "\u00b8": 118, "\u00f6": 180, "\u00d4": 146, "\u00e4": 162, "\u00ee": 172, "\u00b1": 111, "1": 18, ".": 15, "\u00cd": 139, "\u013c": 250, "D": 37, "\u012d": 235, "m": 78, "\u00e7": 165, "\u013f": 253, "\u0141": 255, "\u00e2": 160, "+": 12, "<|endoftext|>": 1, "\u0118": 214, "\u00c0": 126, "\u00cb": 137, "\u00d2": 144, ";": 28, "z": 91, "F": 39, "\u00d0": 142, "\u0143": 257, "'": 8, "[": 60, "\u00df": 157, "\u00fb": 185, "\u00ed": 171, "\u0109": 199, "i": 74, "\u0110": 206, "\u0103": 193, "\u012e": 236, "/": 16, "\u00ff": 189, "\u00fa": 184, "\u0111": 207, "\u013b": 249, "\u013d": 251, "\u00b9": 119, "\u00da": 152, "\\": 61, "q": 82, "\u00f0": 174, "\u0115": 211, "\u00a6": 101, "\u0121": 223, "\u0112": 208, ",": 13, ">": 31, "v": 87, "\u0123": 225, "&": 7, "\u00cc": 138, "\u00c2": 128, "k": 76, "e": 70, "\u010c": 202, "\u012a": 232, "p": 81, "\u00e8": 166, "^": 63, "\u00b6": 116, "I": 42, "\u0126": 228, "Z": 59, "M": 46, "\u00b2": 112, "\u011e": 220, "\u00c3": 129, "\u00ea": 168, "\u00ec": 170, "\u012c": 234, "x": 89, "\u00bb": 121, "\u0102": 192, "w": 88, "\u00b7": 117, "_": 64, "\u0136": 244, "\u00c6": 132, "\u0122": 224, "o": 80, "\u00c8": 134, "\"": 3, "\u0104": 194, "\u0138": 246, "2": 19, "\u00c7": 133, "\u00ca": 136, "\u00f1": 175, ")": 10, "\u0106": 196, "]": 62, "\u00f8": 182, "t": 85, "\u0116": 212, "\u0117": 213, "\u010f": 205, "\u00bf": 125, "\u0101": 191, "=": 30, "\u00ae": 108, "\u0128": 230, "4": 21, "6": 23, "?": 32, "\u00cf": 141, "\u00a8": 103, "b": 67, "\u0108": 198, "\u00e0": 158, "\u00af": 109, "\u0124": 226, "3": 20, "\u00e6": 164, "\u0127": 229, "\u010e": 204, "\u00de": 156, "\u010b": 201, "\u00a9": 104, "Q": 50, "\u00e5": 163, "\u00d3": 145, "\u010d": 203, "ng": 258, "er": 259, "ur": 260, "he": 261, "nd": 262, "ss": 263, "gh": 264, "ge": 265, "en": 266, "gr": 267, "up": 268, "ke": 269, "dy": 270, "de": 271, "nt": 272, "rd": 273, "dg": 274, "ve": 275, "rt": 276, "ar": 277, "pl": 278, "in": 279, "ld": 280, "rg": 281, "ly": 282, "ro": 283, "ed": 284, "an": 285, "mb": 286, "te": 287, "nc": 288, "le": 289, "el": 290, "ul": 291, "us": 292, "ym": 293, "qu": 294, "gu": 295, "ll": 296, "wn": 297, "rk": 298, "her": 299, "um": 300, "ig": 301, "es": 302, "ce": 303, "em": 304, "ib": 305, "tr": 306, "on": 307, "cl": 308, "ma": 309, "se": 310, "li": 311, "me": 312, "th": 313, "bl": 314, "den": 315, "gn": 316, "ow": 317, "rc": 318, "at": 319, "et": 320, "ch": 321, "du": 322, "ud": 323, "al": 324, "uc": 325, "ug": 326, "iv": 327, "bu": 328, "and": 329, "ut": 330, "sh": 331, "la": 332, "ec": 333, "io": 334, "ard": 335, "ra": 336, "om": 337, "ou": 338, "og": 339, "ct": 340, "oup": 341, "vi": 342, "dro": 343, "ti": 344, "ent": 345, "ck": 346, "ple": 347, "ue": 348, "ing": 349, "mal": 350, "or": 351, "po": 352, "re": 353, "lt": 354, "rn": 355, "st": 356, "od": 357, "rm": 358, "ag": 359, "sk": 360, "ea": 361, "to": 362, "il": 363, "bi": 364, "the": 365, "ey": 366, "und": 367, "ia": 368, "hi": 369, "ri": 370, "ugh": 371, "am": 372, "ca": 373, "get": 374, "it": 375, "ic": 376, "ak": 377, "ht": 378, "rv": 379, "but": 380, "ay": 381, "na": 382, "as": 383, "ad": 384, "nce": 385, "un": 386, "ns": 387, "su": 388, "ir": 389, "ty": 390, "ov": 391, "tu": 392, "oy": 393, "ap": 394, "gd": 395, "ip": 396, "rom": 397, "tur": 398, "ect": 399, "ff": 400, "ion": 401, "im": 402, "lo": 403, "pt": 404, "use": 405, "ui": 406, "ish": 407, "ne": 408, "di": 409, "av": 410, "ga": 411, "no": 412, "op": 413, "ger": 414, "is": 415, "drom": 416, "ie": 417, "we": 418, "ph": 419, "da": 420, "rr": 421, "mat": 422, "mo": 423, "be": 424, "ai": 425, "id": 426, "lly": 427, "gra": 428, "ure": 429, "ler": 430, "ac": 431, "ha": 432, "der": 433, "do": 434, "nk": 435, "age": 436, "si": 437, "mp": 438, "dl": 439, "igh": 440, "ba": 441, "ol": 442, "ua": 443, "ab": 444, "ther": 445, "ess": 446, "rde": 447, "vel": 448, "ni": 449, "tem": 450, "rch": 451, "lem": 452, "ci": 453, "mu": 454, "ber": 455, "men": 456, "os": 457, "mn": 458, "ko": 459, "ase": 460, "ver": 461, "oo": 462, "dr": 463, "ide": 464, "rap": 465, "ate": 466, "est": 467, "rty": 468, "va": 469, "cu": 470, "ee": 471, "pe": 472, "lf": 473, "ft": 474, "ho": 475, "tt": 476, "ta": 477, "eg": 478, "icl": 479, "lio": 480, "mi": 481, "cer": 482, "yl": 483, "ok": 484, "ork": 485, "ka": 486, "fe": 487, "ry": 488, "ult": 489, "ltur": 490, "lu": 491, "ram": 492, "ethe": 493, "ev": 494, "nat": 495, "rs": 496, "tl": 497, "ght": 498, "tion": 499}
|