End of training
Browse files- .gitignore +1 -0
- added_tokens.json +3 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +305 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +724 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +1 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 340
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 340,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 340,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 20,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.30.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 341
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 340,
|
4 |
+
"eos_token_id": 340,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
merges.txt
ADDED
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#version: 0.2
|
2 |
+
A A
|
3 |
+
F F
|
4 |
+
H H
|
5 |
+
X X
|
6 |
+
U U
|
7 |
+
B B
|
8 |
+
S S
|
9 |
+
V V
|
10 |
+
O O
|
11 |
+
C C
|
12 |
+
Y Y
|
13 |
+
L L
|
14 |
+
M M
|
15 |
+
T T
|
16 |
+
N N
|
17 |
+
\ \
|
18 |
+
] ]
|
19 |
+
J J
|
20 |
+
Q Q
|
21 |
+
[ [
|
22 |
+
I I
|
23 |
+
G G
|
24 |
+
P P
|
25 |
+
` `
|
26 |
+
_ _
|
27 |
+
R R
|
28 |
+
^ ^
|
29 |
+
D D
|
30 |
+
Z Z
|
31 |
+
K K
|
32 |
+
W W
|
33 |
+
E E
|
34 |
+
AA AA
|
35 |
+
XX XX
|
36 |
+
FF FF
|
37 |
+
HH HH
|
38 |
+
UU UU
|
39 |
+
BB BB
|
40 |
+
VV VV
|
41 |
+
SS SS
|
42 |
+
LL LL
|
43 |
+
MM MM
|
44 |
+
NN NN
|
45 |
+
OO OO
|
46 |
+
CC CC
|
47 |
+
YY YY
|
48 |
+
TT TT
|
49 |
+
\\ \\
|
50 |
+
JJ JJ
|
51 |
+
]] ]]
|
52 |
+
[[ [[
|
53 |
+
QQ QQ
|
54 |
+
RR RR
|
55 |
+
II II
|
56 |
+
GG GG
|
57 |
+
PP PP
|
58 |
+
`` ``
|
59 |
+
__ __
|
60 |
+
^^ ^^
|
61 |
+
KK KK
|
62 |
+
ZZ ZZ
|
63 |
+
DD DD
|
64 |
+
WW WW
|
65 |
+
EE EE
|
66 |
+
FF F
|
67 |
+
HH H
|
68 |
+
AA A
|
69 |
+
UU U
|
70 |
+
YY Y
|
71 |
+
SS S
|
72 |
+
OO O
|
73 |
+
XX X
|
74 |
+
TT T
|
75 |
+
BB B
|
76 |
+
]] ]
|
77 |
+
\\ \
|
78 |
+
CC C
|
79 |
+
GG G
|
80 |
+
QQ Q
|
81 |
+
VV V
|
82 |
+
LL L
|
83 |
+
MM M
|
84 |
+
NN N
|
85 |
+
JJ J
|
86 |
+
II I
|
87 |
+
[[ [
|
88 |
+
DD D
|
89 |
+
__ _
|
90 |
+
PP P
|
91 |
+
WW W
|
92 |
+
^^ ^
|
93 |
+
ZZ Z
|
94 |
+
EE E
|
95 |
+
`` `
|
96 |
+
KK K
|
97 |
+
RR R
|
98 |
+
HHHH H
|
99 |
+
FFFF F
|
100 |
+
AAAA A
|
101 |
+
BBBB B
|
102 |
+
XXXX X
|
103 |
+
UUUU U
|
104 |
+
CCCC C
|
105 |
+
OOOO O
|
106 |
+
SSSS S
|
107 |
+
YYYY Y
|
108 |
+
VVVV V
|
109 |
+
TTTT T
|
110 |
+
LLLL L
|
111 |
+
\\\\ \
|
112 |
+
JJJJ J
|
113 |
+
NNNN N
|
114 |
+
]]]] ]
|
115 |
+
MMMM M
|
116 |
+
GGGG G
|
117 |
+
QQQQ Q
|
118 |
+
[[[[ [
|
119 |
+
IIII I
|
120 |
+
```` `
|
121 |
+
PPPP P
|
122 |
+
^^^^ ^
|
123 |
+
____ _
|
124 |
+
DDDD D
|
125 |
+
XXXX XXXX
|
126 |
+
KKKK K
|
127 |
+
AAAA AAAA
|
128 |
+
RRRR RRRR
|
129 |
+
ZZZZ Z
|
130 |
+
EEEE E
|
131 |
+
WWWW W
|
132 |
+
VVVV VVVV
|
133 |
+
UUUU UUUU
|
134 |
+
HHHH HH
|
135 |
+
FFFF FFFF
|
136 |
+
BBBB BB
|
137 |
+
RRRR R
|
138 |
+
MMMM MM
|
139 |
+
CCCC CC
|
140 |
+
SSSS SS
|
141 |
+
NNNN NNNN
|
142 |
+
AAAA AA
|
143 |
+
LLLL LL
|
144 |
+
OOOO OO
|
145 |
+
FFFF FF
|
146 |
+
]]]] ]]
|
147 |
+
YYYY YY
|
148 |
+
JJJJ JJ
|
149 |
+
\\\\ \\
|
150 |
+
TTTT TT
|
151 |
+
XXXX XX
|
152 |
+
[[[[ [[
|
153 |
+
IIII II
|
154 |
+
BBBB BBBB
|
155 |
+
QQQQ QQ
|
156 |
+
UUUU UU
|
157 |
+
GGGG GG
|
158 |
+
HHHH HHHH
|
159 |
+
PPPP PP
|
160 |
+
MMMM MMMM
|
161 |
+
```` ``
|
162 |
+
KKKK KK
|
163 |
+
VVVV VV
|
164 |
+
^^^^ ^^
|
165 |
+
NNNN NN
|
166 |
+
____ __
|
167 |
+
SSSS SSSS
|
168 |
+
ZZZZ ZZ
|
169 |
+
LLLL LLLL
|
170 |
+
EEEE EE
|
171 |
+
DDDD DD
|
172 |
+
WWWW WW
|
173 |
+
OOOO OOOO
|
174 |
+
\\\\ \\\\
|
175 |
+
YYYY YYYY
|
176 |
+
TTTT TTTT
|
177 |
+
CCCC CCCC
|
178 |
+
RRRR RR
|
179 |
+
[[[[ [[[[
|
180 |
+
JJJJ JJJJ
|
181 |
+
AAAA AAA
|
182 |
+
]]]] ]]]]
|
183 |
+
IIII IIII
|
184 |
+
QQQQ QQQQ
|
185 |
+
FFFF FFF
|
186 |
+
XXXX XXX
|
187 |
+
HHHH HHH
|
188 |
+
```` ````
|
189 |
+
PPPP PPPP
|
190 |
+
BBBB BBB
|
191 |
+
UUUU UUU
|
192 |
+
LLLL LLL
|
193 |
+
TTTT TTT
|
194 |
+
VVVV VVV
|
195 |
+
NNNN NNN
|
196 |
+
KKKK KKKK
|
197 |
+
____ ____
|
198 |
+
CCCC CCC
|
199 |
+
\\\\ \\\
|
200 |
+
SSSS SSS
|
201 |
+
^^^^ ^^^^
|
202 |
+
MMMM MMM
|
203 |
+
OOOO OOO
|
204 |
+
YYYY YYY
|
205 |
+
GGGG GGGG
|
206 |
+
]]]] ]]]
|
207 |
+
QQQQ QQQ
|
208 |
+
[[[[ [[[
|
209 |
+
IIII III
|
210 |
+
JJJJ JJJ
|
211 |
+
DDDD DDD
|
212 |
+
ZZZZ ZZZZ
|
213 |
+
WWWW WWWW
|
214 |
+
RRRR RRR
|
215 |
+
EEEE EEEE
|
216 |
+
```` ```
|
217 |
+
GGGG GGG
|
218 |
+
PPPP PPP
|
219 |
+
^^^^ ^^^
|
220 |
+
KKKK KKK
|
221 |
+
____ ___
|
222 |
+
ZZZZ ZZZ
|
223 |
+
WWWW WWW
|
224 |
+
EEEE EEE
|
225 |
+
DDDD DDDD
|
226 |
+
AAAA AAAAA
|
227 |
+
FFFF FFFFF
|
228 |
+
XXXX XXXXX
|
229 |
+
UUUU UUUUU
|
230 |
+
HHHH HHHHH
|
231 |
+
BBBB BBBBB
|
232 |
+
LLLL LLLLL
|
233 |
+
VVVV VVVVV
|
234 |
+
NNNN NNNNN
|
235 |
+
SSSS SSSSS
|
236 |
+
MMMM MMMMM
|
237 |
+
OOOO OOOOO
|
238 |
+
TTTT TTTTT
|
239 |
+
CCCC CCCCC
|
240 |
+
[[[[ [[[[[
|
241 |
+
\\\\ \\\\\
|
242 |
+
RRRRRRRR R
|
243 |
+
YYYY YYYYY
|
244 |
+
JJJJ JJJJJ
|
245 |
+
]]]] ]]]]]
|
246 |
+
QQQQ QQQQQ
|
247 |
+
AAAAAAAA AA
|
248 |
+
IIII IIIII
|
249 |
+
KKKK KKKKK
|
250 |
+
```` `````
|
251 |
+
XXXXXXXX XX
|
252 |
+
VVVVVVVV VV
|
253 |
+
____ _____
|
254 |
+
GGGG GGGGG
|
255 |
+
PPPP PPPPP
|
256 |
+
UUUUUUUU UU
|
257 |
+
HHHH HHHHHH
|
258 |
+
^^^^ ^^^^^
|
259 |
+
BBBB BBBBBB
|
260 |
+
NNNNNNNN NN
|
261 |
+
WWWW WWWWW
|
262 |
+
LLLL LLLLLL
|
263 |
+
FFFFFFFF FF
|
264 |
+
MMMM MMMMMM
|
265 |
+
EEEE EEEEE
|
266 |
+
ZZZZ ZZZZZ
|
267 |
+
SSSS SSSSSS
|
268 |
+
DDDD DDDDD
|
269 |
+
CCCC CCCCCC
|
270 |
+
AAAAAAAA AAA
|
271 |
+
XXXXXXXX XXX
|
272 |
+
JJJJ JJJJJJ
|
273 |
+
YYYY YYYYYY
|
274 |
+
\\\\ \\\\\\
|
275 |
+
TTTT TTTTTT
|
276 |
+
QQQQ QQQQQQ
|
277 |
+
RRRRRRRR RR
|
278 |
+
[[[[ [[[[[[
|
279 |
+
]]]] ]]]]]]
|
280 |
+
UUUUUUUU UUU
|
281 |
+
OOOO OOOOOO
|
282 |
+
KKKK KKKKKK
|
283 |
+
HHHHHHHH HHH
|
284 |
+
FFFFFFFF FFF
|
285 |
+
IIII IIIIII
|
286 |
+
VVVVVVVV VVV
|
287 |
+
BBBBBBBB BBB
|
288 |
+
NNNNNNNN NNN
|
289 |
+
RRRRRRRR RRR
|
290 |
+
PPPP PPPPPP
|
291 |
+
GGGG GGGGGG
|
292 |
+
```` ``````
|
293 |
+
^^^^ ^^^^^^
|
294 |
+
MMMMMMMM MMM
|
295 |
+
LLLLLLLL LLL
|
296 |
+
____ ______
|
297 |
+
ZZZZ ZZZZZZ
|
298 |
+
WWWW WWWWWW
|
299 |
+
JJJJJJJJ JJJ
|
300 |
+
AAAAAAAA AAAA
|
301 |
+
XXXXXXXX XXXX
|
302 |
+
DDDD DDDDDD
|
303 |
+
SSSSSSSS SSS
|
304 |
+
RRRRRRRR RRRRRRRR
|
305 |
+
\\\\\\\\ \\\
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2995daa39ab7118dbffd5becc26cac4db22921f32693e1485384a67be6d7e1
|
3 |
+
size 344465245
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,724 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 20,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": null,
|
10 |
+
"added_tokens": [
|
11 |
+
{
|
12 |
+
"id": 0,
|
13 |
+
"content": "<[|endoftext|>]",
|
14 |
+
"single_word": false,
|
15 |
+
"lstrip": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"id": 1,
|
22 |
+
"content": "...",
|
23 |
+
"single_word": false,
|
24 |
+
"lstrip": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"id": 2,
|
31 |
+
"content": "\n",
|
32 |
+
"single_word": false,
|
33 |
+
"lstrip": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"id": 340,
|
40 |
+
"content": "<|endoftext|>",
|
41 |
+
"single_word": false,
|
42 |
+
"lstrip": false,
|
43 |
+
"rstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"special": true
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"normalizer": null,
|
49 |
+
"pre_tokenizer": {
|
50 |
+
"type": "ByteLevel",
|
51 |
+
"add_prefix_space": false,
|
52 |
+
"trim_offsets": true,
|
53 |
+
"use_regex": true
|
54 |
+
},
|
55 |
+
"post_processor": {
|
56 |
+
"type": "ByteLevel",
|
57 |
+
"add_prefix_space": true,
|
58 |
+
"trim_offsets": false,
|
59 |
+
"use_regex": true
|
60 |
+
},
|
61 |
+
"decoder": {
|
62 |
+
"type": "ByteLevel",
|
63 |
+
"add_prefix_space": true,
|
64 |
+
"trim_offsets": true,
|
65 |
+
"use_regex": true
|
66 |
+
},
|
67 |
+
"model": {
|
68 |
+
"type": "BPE",
|
69 |
+
"dropout": null,
|
70 |
+
"unk_token": null,
|
71 |
+
"continuing_subword_prefix": null,
|
72 |
+
"end_of_word_suffix": null,
|
73 |
+
"fuse_unk": false,
|
74 |
+
"byte_fallback": false,
|
75 |
+
"vocab": {
|
76 |
+
"<[|endoftext|>]": 0,
|
77 |
+
"...": 1,
|
78 |
+
"\n": 2,
|
79 |
+
"A": 3,
|
80 |
+
"B": 4,
|
81 |
+
"C": 5,
|
82 |
+
"D": 6,
|
83 |
+
"E": 7,
|
84 |
+
"F": 8,
|
85 |
+
"G": 9,
|
86 |
+
"H": 10,
|
87 |
+
"I": 11,
|
88 |
+
"J": 12,
|
89 |
+
"K": 13,
|
90 |
+
"L": 14,
|
91 |
+
"M": 15,
|
92 |
+
"N": 16,
|
93 |
+
"O": 17,
|
94 |
+
"P": 18,
|
95 |
+
"Q": 19,
|
96 |
+
"R": 20,
|
97 |
+
"S": 21,
|
98 |
+
"T": 22,
|
99 |
+
"U": 23,
|
100 |
+
"V": 24,
|
101 |
+
"W": 25,
|
102 |
+
"X": 26,
|
103 |
+
"Y": 27,
|
104 |
+
"Z": 28,
|
105 |
+
"[": 29,
|
106 |
+
"\\": 30,
|
107 |
+
"]": 31,
|
108 |
+
"^": 32,
|
109 |
+
"_": 33,
|
110 |
+
"`": 34,
|
111 |
+
"Ċ": 35,
|
112 |
+
"AA": 36,
|
113 |
+
"FF": 37,
|
114 |
+
"HH": 38,
|
115 |
+
"XX": 39,
|
116 |
+
"UU": 40,
|
117 |
+
"BB": 41,
|
118 |
+
"SS": 42,
|
119 |
+
"VV": 43,
|
120 |
+
"OO": 44,
|
121 |
+
"CC": 45,
|
122 |
+
"YY": 46,
|
123 |
+
"LL": 47,
|
124 |
+
"MM": 48,
|
125 |
+
"TT": 49,
|
126 |
+
"NN": 50,
|
127 |
+
"\\\\": 51,
|
128 |
+
"]]": 52,
|
129 |
+
"JJ": 53,
|
130 |
+
"QQ": 54,
|
131 |
+
"[[": 55,
|
132 |
+
"II": 56,
|
133 |
+
"GG": 57,
|
134 |
+
"PP": 58,
|
135 |
+
"``": 59,
|
136 |
+
"__": 60,
|
137 |
+
"RR": 61,
|
138 |
+
"^^": 62,
|
139 |
+
"DD": 63,
|
140 |
+
"ZZ": 64,
|
141 |
+
"KK": 65,
|
142 |
+
"WW": 66,
|
143 |
+
"EE": 67,
|
144 |
+
"AAAA": 68,
|
145 |
+
"XXXX": 69,
|
146 |
+
"FFFF": 70,
|
147 |
+
"HHHH": 71,
|
148 |
+
"UUUU": 72,
|
149 |
+
"BBBB": 73,
|
150 |
+
"VVVV": 74,
|
151 |
+
"SSSS": 75,
|
152 |
+
"LLLL": 76,
|
153 |
+
"MMMM": 77,
|
154 |
+
"NNNN": 78,
|
155 |
+
"OOOO": 79,
|
156 |
+
"CCCC": 80,
|
157 |
+
"YYYY": 81,
|
158 |
+
"TTTT": 82,
|
159 |
+
"\\\\\\\\": 83,
|
160 |
+
"JJJJ": 84,
|
161 |
+
"]]]]": 85,
|
162 |
+
"[[[[": 86,
|
163 |
+
"QQQQ": 87,
|
164 |
+
"RRRR": 88,
|
165 |
+
"IIII": 89,
|
166 |
+
"GGGG": 90,
|
167 |
+
"PPPP": 91,
|
168 |
+
"````": 92,
|
169 |
+
"____": 93,
|
170 |
+
"^^^^": 94,
|
171 |
+
"KKKK": 95,
|
172 |
+
"ZZZZ": 96,
|
173 |
+
"DDDD": 97,
|
174 |
+
"WWWW": 98,
|
175 |
+
"EEEE": 99,
|
176 |
+
"FFF": 100,
|
177 |
+
"HHH": 101,
|
178 |
+
"AAA": 102,
|
179 |
+
"UUU": 103,
|
180 |
+
"YYY": 104,
|
181 |
+
"SSS": 105,
|
182 |
+
"OOO": 106,
|
183 |
+
"XXX": 107,
|
184 |
+
"TTT": 108,
|
185 |
+
"BBB": 109,
|
186 |
+
"]]]": 110,
|
187 |
+
"\\\\\\": 111,
|
188 |
+
"CCC": 112,
|
189 |
+
"GGG": 113,
|
190 |
+
"QQQ": 114,
|
191 |
+
"VVV": 115,
|
192 |
+
"LLL": 116,
|
193 |
+
"MMM": 117,
|
194 |
+
"NNN": 118,
|
195 |
+
"JJJ": 119,
|
196 |
+
"III": 120,
|
197 |
+
"[[[": 121,
|
198 |
+
"DDD": 122,
|
199 |
+
"___": 123,
|
200 |
+
"PPP": 124,
|
201 |
+
"WWW": 125,
|
202 |
+
"^^^": 126,
|
203 |
+
"ZZZ": 127,
|
204 |
+
"EEE": 128,
|
205 |
+
"```": 129,
|
206 |
+
"KKK": 130,
|
207 |
+
"RRR": 131,
|
208 |
+
"HHHHH": 132,
|
209 |
+
"FFFFF": 133,
|
210 |
+
"AAAAA": 134,
|
211 |
+
"BBBBB": 135,
|
212 |
+
"XXXXX": 136,
|
213 |
+
"UUUUU": 137,
|
214 |
+
"CCCCC": 138,
|
215 |
+
"OOOOO": 139,
|
216 |
+
"SSSSS": 140,
|
217 |
+
"YYYYY": 141,
|
218 |
+
"VVVVV": 142,
|
219 |
+
"TTTTT": 143,
|
220 |
+
"LLLLL": 144,
|
221 |
+
"\\\\\\\\\\": 145,
|
222 |
+
"JJJJJ": 146,
|
223 |
+
"NNNNN": 147,
|
224 |
+
"]]]]]": 148,
|
225 |
+
"MMMMM": 149,
|
226 |
+
"GGGGG": 150,
|
227 |
+
"QQQQQ": 151,
|
228 |
+
"[[[[[": 152,
|
229 |
+
"IIIII": 153,
|
230 |
+
"`````": 154,
|
231 |
+
"PPPPP": 155,
|
232 |
+
"^^^^^": 156,
|
233 |
+
"_____": 157,
|
234 |
+
"DDDDD": 158,
|
235 |
+
"XXXXXXXX": 159,
|
236 |
+
"KKKKK": 160,
|
237 |
+
"AAAAAAAA": 161,
|
238 |
+
"RRRRRRRR": 162,
|
239 |
+
"ZZZZZ": 163,
|
240 |
+
"EEEEE": 164,
|
241 |
+
"WWWWW": 165,
|
242 |
+
"VVVVVVVV": 166,
|
243 |
+
"UUUUUUUU": 167,
|
244 |
+
"HHHHHH": 168,
|
245 |
+
"FFFFFFFF": 169,
|
246 |
+
"BBBBBB": 170,
|
247 |
+
"RRRRR": 171,
|
248 |
+
"MMMMMM": 172,
|
249 |
+
"CCCCCC": 173,
|
250 |
+
"SSSSSS": 174,
|
251 |
+
"NNNNNNNN": 175,
|
252 |
+
"AAAAAA": 176,
|
253 |
+
"LLLLLL": 177,
|
254 |
+
"OOOOOO": 178,
|
255 |
+
"FFFFFF": 179,
|
256 |
+
"]]]]]]": 180,
|
257 |
+
"YYYYYY": 181,
|
258 |
+
"JJJJJJ": 182,
|
259 |
+
"\\\\\\\\\\\\": 183,
|
260 |
+
"TTTTTT": 184,
|
261 |
+
"XXXXXX": 185,
|
262 |
+
"[[[[[[": 186,
|
263 |
+
"IIIIII": 187,
|
264 |
+
"BBBBBBBB": 188,
|
265 |
+
"QQQQQQ": 189,
|
266 |
+
"UUUUUU": 190,
|
267 |
+
"GGGGGG": 191,
|
268 |
+
"HHHHHHHH": 192,
|
269 |
+
"PPPPPP": 193,
|
270 |
+
"MMMMMMMM": 194,
|
271 |
+
"``````": 195,
|
272 |
+
"KKKKKK": 196,
|
273 |
+
"VVVVVV": 197,
|
274 |
+
"^^^^^^": 198,
|
275 |
+
"NNNNNN": 199,
|
276 |
+
"______": 200,
|
277 |
+
"SSSSSSSS": 201,
|
278 |
+
"ZZZZZZ": 202,
|
279 |
+
"LLLLLLLL": 203,
|
280 |
+
"EEEEEE": 204,
|
281 |
+
"DDDDDD": 205,
|
282 |
+
"WWWWWW": 206,
|
283 |
+
"OOOOOOOO": 207,
|
284 |
+
"\\\\\\\\\\\\\\\\": 208,
|
285 |
+
"YYYYYYYY": 209,
|
286 |
+
"TTTTTTTT": 210,
|
287 |
+
"CCCCCCCC": 211,
|
288 |
+
"RRRRRR": 212,
|
289 |
+
"[[[[[[[[": 213,
|
290 |
+
"JJJJJJJJ": 214,
|
291 |
+
"AAAAAAA": 215,
|
292 |
+
"]]]]]]]]": 216,
|
293 |
+
"IIIIIIII": 217,
|
294 |
+
"QQQQQQQQ": 218,
|
295 |
+
"FFFFFFF": 219,
|
296 |
+
"XXXXXXX": 220,
|
297 |
+
"HHHHHHH": 221,
|
298 |
+
"````````": 222,
|
299 |
+
"PPPPPPPP": 223,
|
300 |
+
"BBBBBBB": 224,
|
301 |
+
"UUUUUUU": 225,
|
302 |
+
"LLLLLLL": 226,
|
303 |
+
"TTTTTTT": 227,
|
304 |
+
"VVVVVVV": 228,
|
305 |
+
"NNNNNNN": 229,
|
306 |
+
"KKKKKKKK": 230,
|
307 |
+
"________": 231,
|
308 |
+
"CCCCCCC": 232,
|
309 |
+
"\\\\\\\\\\\\\\": 233,
|
310 |
+
"SSSSSSS": 234,
|
311 |
+
"^^^^^^^^": 235,
|
312 |
+
"MMMMMMM": 236,
|
313 |
+
"OOOOOOO": 237,
|
314 |
+
"YYYYYYY": 238,
|
315 |
+
"GGGGGGGG": 239,
|
316 |
+
"]]]]]]]": 240,
|
317 |
+
"QQQQQQQ": 241,
|
318 |
+
"[[[[[[[": 242,
|
319 |
+
"IIIIIII": 243,
|
320 |
+
"JJJJJJJ": 244,
|
321 |
+
"DDDDDDD": 245,
|
322 |
+
"ZZZZZZZZ": 246,
|
323 |
+
"WWWWWWWW": 247,
|
324 |
+
"RRRRRRR": 248,
|
325 |
+
"EEEEEEEE": 249,
|
326 |
+
"```````": 250,
|
327 |
+
"GGGGGGG": 251,
|
328 |
+
"PPPPPPP": 252,
|
329 |
+
"^^^^^^^": 253,
|
330 |
+
"KKKKKKK": 254,
|
331 |
+
"_______": 255,
|
332 |
+
"ZZZZZZZ": 256,
|
333 |
+
"WWWWWWW": 257,
|
334 |
+
"EEEEEEE": 258,
|
335 |
+
"DDDDDDDD": 259,
|
336 |
+
"AAAAAAAAA": 260,
|
337 |
+
"FFFFFFFFF": 261,
|
338 |
+
"XXXXXXXXX": 262,
|
339 |
+
"UUUUUUUUU": 263,
|
340 |
+
"HHHHHHHHH": 264,
|
341 |
+
"BBBBBBBBB": 265,
|
342 |
+
"LLLLLLLLL": 266,
|
343 |
+
"VVVVVVVVV": 267,
|
344 |
+
"NNNNNNNNN": 268,
|
345 |
+
"SSSSSSSSS": 269,
|
346 |
+
"MMMMMMMMM": 270,
|
347 |
+
"OOOOOOOOO": 271,
|
348 |
+
"TTTTTTTTT": 272,
|
349 |
+
"CCCCCCCCC": 273,
|
350 |
+
"[[[[[[[[[": 274,
|
351 |
+
"\\\\\\\\\\\\\\\\\\": 275,
|
352 |
+
"RRRRRRRRR": 276,
|
353 |
+
"YYYYYYYYY": 277,
|
354 |
+
"JJJJJJJJJ": 278,
|
355 |
+
"]]]]]]]]]": 279,
|
356 |
+
"QQQQQQQQQ": 280,
|
357 |
+
"AAAAAAAAAA": 281,
|
358 |
+
"IIIIIIIII": 282,
|
359 |
+
"KKKKKKKKK": 283,
|
360 |
+
"`````````": 284,
|
361 |
+
"XXXXXXXXXX": 285,
|
362 |
+
"VVVVVVVVVV": 286,
|
363 |
+
"_________": 287,
|
364 |
+
"GGGGGGGGG": 288,
|
365 |
+
"PPPPPPPPP": 289,
|
366 |
+
"UUUUUUUUUU": 290,
|
367 |
+
"HHHHHHHHHH": 291,
|
368 |
+
"^^^^^^^^^": 292,
|
369 |
+
"BBBBBBBBBB": 293,
|
370 |
+
"NNNNNNNNNN": 294,
|
371 |
+
"WWWWWWWWW": 295,
|
372 |
+
"LLLLLLLLLL": 296,
|
373 |
+
"FFFFFFFFFF": 297,
|
374 |
+
"MMMMMMMMMM": 298,
|
375 |
+
"EEEEEEEEE": 299,
|
376 |
+
"ZZZZZZZZZ": 300,
|
377 |
+
"SSSSSSSSSS": 301,
|
378 |
+
"DDDDDDDDD": 302,
|
379 |
+
"CCCCCCCCCC": 303,
|
380 |
+
"AAAAAAAAAAA": 304,
|
381 |
+
"XXXXXXXXXXX": 305,
|
382 |
+
"JJJJJJJJJJ": 306,
|
383 |
+
"YYYYYYYYYY": 307,
|
384 |
+
"\\\\\\\\\\\\\\\\\\\\": 308,
|
385 |
+
"TTTTTTTTTT": 309,
|
386 |
+
"QQQQQQQQQQ": 310,
|
387 |
+
"RRRRRRRRRR": 311,
|
388 |
+
"[[[[[[[[[[": 312,
|
389 |
+
"]]]]]]]]]]": 313,
|
390 |
+
"UUUUUUUUUUU": 314,
|
391 |
+
"OOOOOOOOOO": 315,
|
392 |
+
"KKKKKKKKKK": 316,
|
393 |
+
"HHHHHHHHHHH": 317,
|
394 |
+
"FFFFFFFFFFF": 318,
|
395 |
+
"IIIIIIIIII": 319,
|
396 |
+
"VVVVVVVVVVV": 320,
|
397 |
+
"BBBBBBBBBBB": 321,
|
398 |
+
"NNNNNNNNNNN": 322,
|
399 |
+
"RRRRRRRRRRR": 323,
|
400 |
+
"PPPPPPPPPP": 324,
|
401 |
+
"GGGGGGGGGG": 325,
|
402 |
+
"``````````": 326,
|
403 |
+
"^^^^^^^^^^": 327,
|
404 |
+
"MMMMMMMMMMM": 328,
|
405 |
+
"LLLLLLLLLLL": 329,
|
406 |
+
"__________": 330,
|
407 |
+
"ZZZZZZZZZZ": 331,
|
408 |
+
"WWWWWWWWWW": 332,
|
409 |
+
"JJJJJJJJJJJ": 333,
|
410 |
+
"AAAAAAAAAAAA": 334,
|
411 |
+
"XXXXXXXXXXXX": 335,
|
412 |
+
"DDDDDDDDDD": 336,
|
413 |
+
"SSSSSSSSSSS": 337,
|
414 |
+
"RRRRRRRRRRRRRRRR": 338,
|
415 |
+
"\\\\\\\\\\\\\\\\\\\\\\": 339
|
416 |
+
},
|
417 |
+
"merges": [
|
418 |
+
"A A",
|
419 |
+
"F F",
|
420 |
+
"H H",
|
421 |
+
"X X",
|
422 |
+
"U U",
|
423 |
+
"B B",
|
424 |
+
"S S",
|
425 |
+
"V V",
|
426 |
+
"O O",
|
427 |
+
"C C",
|
428 |
+
"Y Y",
|
429 |
+
"L L",
|
430 |
+
"M M",
|
431 |
+
"T T",
|
432 |
+
"N N",
|
433 |
+
"\\ \\",
|
434 |
+
"] ]",
|
435 |
+
"J J",
|
436 |
+
"Q Q",
|
437 |
+
"[ [",
|
438 |
+
"I I",
|
439 |
+
"G G",
|
440 |
+
"P P",
|
441 |
+
"` `",
|
442 |
+
"_ _",
|
443 |
+
"R R",
|
444 |
+
"^ ^",
|
445 |
+
"D D",
|
446 |
+
"Z Z",
|
447 |
+
"K K",
|
448 |
+
"W W",
|
449 |
+
"E E",
|
450 |
+
"AA AA",
|
451 |
+
"XX XX",
|
452 |
+
"FF FF",
|
453 |
+
"HH HH",
|
454 |
+
"UU UU",
|
455 |
+
"BB BB",
|
456 |
+
"VV VV",
|
457 |
+
"SS SS",
|
458 |
+
"LL LL",
|
459 |
+
"MM MM",
|
460 |
+
"NN NN",
|
461 |
+
"OO OO",
|
462 |
+
"CC CC",
|
463 |
+
"YY YY",
|
464 |
+
"TT TT",
|
465 |
+
"\\\\ \\\\",
|
466 |
+
"JJ JJ",
|
467 |
+
"]] ]]",
|
468 |
+
"[[ [[",
|
469 |
+
"QQ QQ",
|
470 |
+
"RR RR",
|
471 |
+
"II II",
|
472 |
+
"GG GG",
|
473 |
+
"PP PP",
|
474 |
+
"`` ``",
|
475 |
+
"__ __",
|
476 |
+
"^^ ^^",
|
477 |
+
"KK KK",
|
478 |
+
"ZZ ZZ",
|
479 |
+
"DD DD",
|
480 |
+
"WW WW",
|
481 |
+
"EE EE",
|
482 |
+
"FF F",
|
483 |
+
"HH H",
|
484 |
+
"AA A",
|
485 |
+
"UU U",
|
486 |
+
"YY Y",
|
487 |
+
"SS S",
|
488 |
+
"OO O",
|
489 |
+
"XX X",
|
490 |
+
"TT T",
|
491 |
+
"BB B",
|
492 |
+
"]] ]",
|
493 |
+
"\\\\ \\",
|
494 |
+
"CC C",
|
495 |
+
"GG G",
|
496 |
+
"QQ Q",
|
497 |
+
"VV V",
|
498 |
+
"LL L",
|
499 |
+
"MM M",
|
500 |
+
"NN N",
|
501 |
+
"JJ J",
|
502 |
+
"II I",
|
503 |
+
"[[ [",
|
504 |
+
"DD D",
|
505 |
+
"__ _",
|
506 |
+
"PP P",
|
507 |
+
"WW W",
|
508 |
+
"^^ ^",
|
509 |
+
"ZZ Z",
|
510 |
+
"EE E",
|
511 |
+
"`` `",
|
512 |
+
"KK K",
|
513 |
+
"RR R",
|
514 |
+
"HHHH H",
|
515 |
+
"FFFF F",
|
516 |
+
"AAAA A",
|
517 |
+
"BBBB B",
|
518 |
+
"XXXX X",
|
519 |
+
"UUUU U",
|
520 |
+
"CCCC C",
|
521 |
+
"OOOO O",
|
522 |
+
"SSSS S",
|
523 |
+
"YYYY Y",
|
524 |
+
"VVVV V",
|
525 |
+
"TTTT T",
|
526 |
+
"LLLL L",
|
527 |
+
"\\\\\\\\ \\",
|
528 |
+
"JJJJ J",
|
529 |
+
"NNNN N",
|
530 |
+
"]]]] ]",
|
531 |
+
"MMMM M",
|
532 |
+
"GGGG G",
|
533 |
+
"QQQQ Q",
|
534 |
+
"[[[[ [",
|
535 |
+
"IIII I",
|
536 |
+
"```` `",
|
537 |
+
"PPPP P",
|
538 |
+
"^^^^ ^",
|
539 |
+
"____ _",
|
540 |
+
"DDDD D",
|
541 |
+
"XXXX XXXX",
|
542 |
+
"KKKK K",
|
543 |
+
"AAAA AAAA",
|
544 |
+
"RRRR RRRR",
|
545 |
+
"ZZZZ Z",
|
546 |
+
"EEEE E",
|
547 |
+
"WWWW W",
|
548 |
+
"VVVV VVVV",
|
549 |
+
"UUUU UUUU",
|
550 |
+
"HHHH HH",
|
551 |
+
"FFFF FFFF",
|
552 |
+
"BBBB BB",
|
553 |
+
"RRRR R",
|
554 |
+
"MMMM MM",
|
555 |
+
"CCCC CC",
|
556 |
+
"SSSS SS",
|
557 |
+
"NNNN NNNN",
|
558 |
+
"AAAA AA",
|
559 |
+
"LLLL LL",
|
560 |
+
"OOOO OO",
|
561 |
+
"FFFF FF",
|
562 |
+
"]]]] ]]",
|
563 |
+
"YYYY YY",
|
564 |
+
"JJJJ JJ",
|
565 |
+
"\\\\\\\\ \\\\",
|
566 |
+
"TTTT TT",
|
567 |
+
"XXXX XX",
|
568 |
+
"[[[[ [[",
|
569 |
+
"IIII II",
|
570 |
+
"BBBB BBBB",
|
571 |
+
"QQQQ QQ",
|
572 |
+
"UUUU UU",
|
573 |
+
"GGGG GG",
|
574 |
+
"HHHH HHHH",
|
575 |
+
"PPPP PP",
|
576 |
+
"MMMM MMMM",
|
577 |
+
"```` ``",
|
578 |
+
"KKKK KK",
|
579 |
+
"VVVV VV",
|
580 |
+
"^^^^ ^^",
|
581 |
+
"NNNN NN",
|
582 |
+
"____ __",
|
583 |
+
"SSSS SSSS",
|
584 |
+
"ZZZZ ZZ",
|
585 |
+
"LLLL LLLL",
|
586 |
+
"EEEE EE",
|
587 |
+
"DDDD DD",
|
588 |
+
"WWWW WW",
|
589 |
+
"OOOO OOOO",
|
590 |
+
"\\\\\\\\ \\\\\\\\",
|
591 |
+
"YYYY YYYY",
|
592 |
+
"TTTT TTTT",
|
593 |
+
"CCCC CCCC",
|
594 |
+
"RRRR RR",
|
595 |
+
"[[[[ [[[[",
|
596 |
+
"JJJJ JJJJ",
|
597 |
+
"AAAA AAA",
|
598 |
+
"]]]] ]]]]",
|
599 |
+
"IIII IIII",
|
600 |
+
"QQQQ QQQQ",
|
601 |
+
"FFFF FFF",
|
602 |
+
"XXXX XXX",
|
603 |
+
"HHHH HHH",
|
604 |
+
"```` ````",
|
605 |
+
"PPPP PPPP",
|
606 |
+
"BBBB BBB",
|
607 |
+
"UUUU UUU",
|
608 |
+
"LLLL LLL",
|
609 |
+
"TTTT TTT",
|
610 |
+
"VVVV VVV",
|
611 |
+
"NNNN NNN",
|
612 |
+
"KKKK KKKK",
|
613 |
+
"____ ____",
|
614 |
+
"CCCC CCC",
|
615 |
+
"\\\\\\\\ \\\\\\",
|
616 |
+
"SSSS SSS",
|
617 |
+
"^^^^ ^^^^",
|
618 |
+
"MMMM MMM",
|
619 |
+
"OOOO OOO",
|
620 |
+
"YYYY YYY",
|
621 |
+
"GGGG GGGG",
|
622 |
+
"]]]] ]]]",
|
623 |
+
"QQQQ QQQ",
|
624 |
+
"[[[[ [[[",
|
625 |
+
"IIII III",
|
626 |
+
"JJJJ JJJ",
|
627 |
+
"DDDD DDD",
|
628 |
+
"ZZZZ ZZZZ",
|
629 |
+
"WWWW WWWW",
|
630 |
+
"RRRR RRR",
|
631 |
+
"EEEE EEEE",
|
632 |
+
"```` ```",
|
633 |
+
"GGGG GGG",
|
634 |
+
"PPPP PPP",
|
635 |
+
"^^^^ ^^^",
|
636 |
+
"KKKK KKK",
|
637 |
+
"____ ___",
|
638 |
+
"ZZZZ ZZZ",
|
639 |
+
"WWWW WWW",
|
640 |
+
"EEEE EEE",
|
641 |
+
"DDDD DDDD",
|
642 |
+
"AAAA AAAAA",
|
643 |
+
"FFFF FFFFF",
|
644 |
+
"XXXX XXXXX",
|
645 |
+
"UUUU UUUUU",
|
646 |
+
"HHHH HHHHH",
|
647 |
+
"BBBB BBBBB",
|
648 |
+
"LLLL LLLLL",
|
649 |
+
"VVVV VVVVV",
|
650 |
+
"NNNN NNNNN",
|
651 |
+
"SSSS SSSSS",
|
652 |
+
"MMMM MMMMM",
|
653 |
+
"OOOO OOOOO",
|
654 |
+
"TTTT TTTTT",
|
655 |
+
"CCCC CCCCC",
|
656 |
+
"[[[[ [[[[[",
|
657 |
+
"\\\\\\\\ \\\\\\\\\\",
|
658 |
+
"RRRRRRRR R",
|
659 |
+
"YYYY YYYYY",
|
660 |
+
"JJJJ JJJJJ",
|
661 |
+
"]]]] ]]]]]",
|
662 |
+
"QQQQ QQQQQ",
|
663 |
+
"AAAAAAAA AA",
|
664 |
+
"IIII IIIII",
|
665 |
+
"KKKK KKKKK",
|
666 |
+
"```` `````",
|
667 |
+
"XXXXXXXX XX",
|
668 |
+
"VVVVVVVV VV",
|
669 |
+
"____ _____",
|
670 |
+
"GGGG GGGGG",
|
671 |
+
"PPPP PPPPP",
|
672 |
+
"UUUUUUUU UU",
|
673 |
+
"HHHH HHHHHH",
|
674 |
+
"^^^^ ^^^^^",
|
675 |
+
"BBBB BBBBBB",
|
676 |
+
"NNNNNNNN NN",
|
677 |
+
"WWWW WWWWW",
|
678 |
+
"LLLL LLLLLL",
|
679 |
+
"FFFFFFFF FF",
|
680 |
+
"MMMM MMMMMM",
|
681 |
+
"EEEE EEEEE",
|
682 |
+
"ZZZZ ZZZZZ",
|
683 |
+
"SSSS SSSSSS",
|
684 |
+
"DDDD DDDDD",
|
685 |
+
"CCCC CCCCCC",
|
686 |
+
"AAAAAAAA AAA",
|
687 |
+
"XXXXXXXX XXX",
|
688 |
+
"JJJJ JJJJJJ",
|
689 |
+
"YYYY YYYYYY",
|
690 |
+
"\\\\\\\\ \\\\\\\\\\\\",
|
691 |
+
"TTTT TTTTTT",
|
692 |
+
"QQQQ QQQQQQ",
|
693 |
+
"RRRRRRRR RR",
|
694 |
+
"[[[[ [[[[[[",
|
695 |
+
"]]]] ]]]]]]",
|
696 |
+
"UUUUUUUU UUU",
|
697 |
+
"OOOO OOOOOO",
|
698 |
+
"KKKK KKKKKK",
|
699 |
+
"HHHHHHHH HHH",
|
700 |
+
"FFFFFFFF FFF",
|
701 |
+
"IIII IIIIII",
|
702 |
+
"VVVVVVVV VVV",
|
703 |
+
"BBBBBBBB BBB",
|
704 |
+
"NNNNNNNN NNN",
|
705 |
+
"RRRRRRRR RRR",
|
706 |
+
"PPPP PPPPPP",
|
707 |
+
"GGGG GGGGGG",
|
708 |
+
"```` ``````",
|
709 |
+
"^^^^ ^^^^^^",
|
710 |
+
"MMMMMMMM MMM",
|
711 |
+
"LLLLLLLL LLL",
|
712 |
+
"____ ______",
|
713 |
+
"ZZZZ ZZZZZZ",
|
714 |
+
"WWWW WWWWWW",
|
715 |
+
"JJJJJJJJ JJJ",
|
716 |
+
"AAAAAAAA AAAA",
|
717 |
+
"XXXXXXXX XXXX",
|
718 |
+
"DDDD DDDDDD",
|
719 |
+
"SSSSSSSS SSS",
|
720 |
+
"RRRRRRRR RRRRRRRR",
|
721 |
+
"\\\\\\\\\\\\\\\\ \\\\\\"
|
722 |
+
]
|
723 |
+
}
|
724 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d14365ae5e7dfbd1b0f3ed2a260269c2f42a1fc8ee16d0a4050af24ff9cb992a
|
3 |
+
size 3899
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<[|endoftext|>]":0,"...":1,"\n":2,"A":3,"B":4,"C":5,"D":6,"E":7,"F":8,"G":9,"H":10,"I":11,"J":12,"K":13,"L":14,"M":15,"N":16,"O":17,"P":18,"Q":19,"R":20,"S":21,"T":22,"U":23,"V":24,"W":25,"X":26,"Y":27,"Z":28,"[":29,"\\":30,"]":31,"^":32,"_":33,"`":34,"Ċ":35,"AA":36,"FF":37,"HH":38,"XX":39,"UU":40,"BB":41,"SS":42,"VV":43,"OO":44,"CC":45,"YY":46,"LL":47,"MM":48,"TT":49,"NN":50,"\\\\":51,"]]":52,"JJ":53,"QQ":54,"[[":55,"II":56,"GG":57,"PP":58,"``":59,"__":60,"RR":61,"^^":62,"DD":63,"ZZ":64,"KK":65,"WW":66,"EE":67,"AAAA":68,"XXXX":69,"FFFF":70,"HHHH":71,"UUUU":72,"BBBB":73,"VVVV":74,"SSSS":75,"LLLL":76,"MMMM":77,"NNNN":78,"OOOO":79,"CCCC":80,"YYYY":81,"TTTT":82,"\\\\\\\\":83,"JJJJ":84,"]]]]":85,"[[[[":86,"QQQQ":87,"RRRR":88,"IIII":89,"GGGG":90,"PPPP":91,"````":92,"____":93,"^^^^":94,"KKKK":95,"ZZZZ":96,"DDDD":97,"WWWW":98,"EEEE":99,"FFF":100,"HHH":101,"AAA":102,"UUU":103,"YYY":104,"SSS":105,"OOO":106,"XXX":107,"TTT":108,"BBB":109,"]]]":110,"\\\\\\":111,"CCC":112,"GGG":113,"QQQ":114,"VVV":115,"LLL":116,"MMM":117,"NNN":118,"JJJ":119,"III":120,"[[[":121,"DDD":122,"___":123,"PPP":124,"WWW":125,"^^^":126,"ZZZ":127,"EEE":128,"```":129,"KKK":130,"RRR":131,"HHHHH":132,"FFFFF":133,"AAAAA":134,"BBBBB":135,"XXXXX":136,"UUUUU":137,"CCCCC":138,"OOOOO":139,"SSSSS":140,"YYYYY":141,"VVVVV":142,"TTTTT":143,"LLLLL":144,"\\\\\\\\\\":145,"JJJJJ":146,"NNNNN":147,"]]]]]":148,"MMMMM":149,"GGGGG":150,"QQQQQ":151,"[[[[[":152,"IIIII":153,"`````":154,"PPPPP":155,"^^^^^":156,"_____":157,"DDDDD":158,"XXXXXXXX":159,"KKKKK":160,"AAAAAAAA":161,"RRRRRRRR":162,"ZZZZZ":163,"EEEEE":164,"WWWWW":165,"VVVVVVVV":166,"UUUUUUUU":167,"HHHHHH":168,"FFFFFFFF":169,"BBBBBB":170,"RRRRR":171,"MMMMMM":172,"CCCCCC":173,"SSSSSS":174,"NNNNNNNN":175,"AAAAAA":176,"LLLLLL":177,"OOOOOO":178,"FFFFFF":179,"]]]]]]":180,"YYYYYY":181,"JJJJJJ":182,"\\\\\\\\\\\\":183,"TTTTTT":184,"XXXXXX":185,"[[[[[[":186,"IIIIII":187,"BBBBBBBB":188,"QQQQQQ":189,"UUUUUU":190,"GGGGGG":191,"HHHHHHHH":192,"PPPPPP":193,"MMMMMMMM":194,"``````":195,"KKKKKK":196,"VVVVVV":197,"^^^^^^":198,"NNNNNN":199,"______":200,"SSSSSSSS":201,"ZZZZZZ":202,"LLLLLLLL":203,"EEEEEE":204,"DDDDDD":205,"WWWWWW":206,"OOOOOOOO":207,"\\\\\\\\\\\\\\\\":208,"YYYYYYYY":209,"TTTTTTTT":210,"CCCCCCCC":211,"RRRRRR":212,"[[[[[[[[":213,"JJJJJJJJ":214,"AAAAAAA":215,"]]]]]]]]":216,"IIIIIIII":217,"QQQQQQQQ":218,"FFFFFFF":219,"XXXXXXX":220,"HHHHHHH":221,"````````":222,"PPPPPPPP":223,"BBBBBBB":224,"UUUUUUU":225,"LLLLLLL":226,"TTTTTTT":227,"VVVVVVV":228,"NNNNNNN":229,"KKKKKKKK":230,"________":231,"CCCCCCC":232,"\\\\\\\\\\\\\\":233,"SSSSSSS":234,"^^^^^^^^":235,"MMMMMMM":236,"OOOOOOO":237,"YYYYYYY":238,"GGGGGGGG":239,"]]]]]]]":240,"QQQQQQQ":241,"[[[[[[[":242,"IIIIIII":243,"JJJJJJJ":244,"DDDDDDD":245,"ZZZZZZZZ":246,"WWWWWWWW":247,"RRRRRRR":248,"EEEEEEEE":249,"```````":250,"GGGGGGG":251,"PPPPPPP":252,"^^^^^^^":253,"KKKKKKK":254,"_______":255,"ZZZZZZZ":256,"WWWWWWW":257,"EEEEEEE":258,"DDDDDDDD":259,"AAAAAAAAA":260,"FFFFFFFFF":261,"XXXXXXXXX":262,"UUUUUUUUU":263,"HHHHHHHHH":264,"BBBBBBBBB":265,"LLLLLLLLL":266,"VVVVVVVVV":267,"NNNNNNNNN":268,"SSSSSSSSS":269,"MMMMMMMMM":270,"OOOOOOOOO":271,"TTTTTTTTT":272,"CCCCCCCCC":273,"[[[[[[[[[":274,"\\\\\\\\\\\\\\\\\\":275,"RRRRRRRRR":276,"YYYYYYYYY":277,"JJJJJJJJJ":278,"]]]]]]]]]":279,"QQQQQQQQQ":280,"AAAAAAAAAA":281,"IIIIIIIII":282,"KKKKKKKKK":283,"`````````":284,"XXXXXXXXXX":285,"VVVVVVVVVV":286,"_________":287,"GGGGGGGGG":288,"PPPPPPPPP":289,"UUUUUUUUUU":290,"HHHHHHHHHH":291,"^^^^^^^^^":292,"BBBBBBBBBB":293,"NNNNNNNNNN":294,"WWWWWWWWW":295,"LLLLLLLLLL":296,"FFFFFFFFFF":297,"MMMMMMMMMM":298,"EEEEEEEEE":299,"ZZZZZZZZZ":300,"SSSSSSSSSS":301,"DDDDDDDDD":302,"CCCCCCCCCC":303,"AAAAAAAAAAA":304,"XXXXXXXXXXX":305,"JJJJJJJJJJ":306,"YYYYYYYYYY":307,"\\\\\\\\\\\\\\\\\\\\":308,"TTTTTTTTTT":309,"QQQQQQQQQQ":310,"RRRRRRRRRR":311,"[[[[[[[[[[":312,"]]]]]]]]]]":313,"UUUUUUUUUUU":314,"OOOOOOOOOO":315,"KKKKKKKKKK":316,"HHHHHHHHHHH":317,"FFFFFFFFFFF":318,"IIIIIIIIII":319,"VVVVVVVVVVV":320,"BBBBBBBBBBB":321,"NNNNNNNNNNN":322,"RRRRRRRRRRR":323,"PPPPPPPPPP":324,"GGGGGGGGGG":325,"``````````":326,"^^^^^^^^^^":327,"MMMMMMMMMMM":328,"LLLLLLLLLLL":329,"__________":330,"ZZZZZZZZZZ":331,"WWWWWWWWWW":332,"JJJJJJJJJJJ":333,"AAAAAAAAAAAA":334,"XXXXXXXXXXXX":335,"DDDDDDDDDD":336,"SSSSSSSSSSS":337,"RRRRRRRRRRRRRRRR":338,"\\\\\\\\\\\\\\\\\\\\\\":339}
|