Upload 9 files
Browse files- added_tokens.json +7 -0
- config.json +27 -0
- errors_25-11-30-16-19-43.txt +27 -0
- merges.txt +507 -0
- pytorch_model.bin +3 -0
- run_args.json +9 -0
- special_tokens_map.json +15 -0
- tokenizer_config.json +106 -0
- vocab.json +769 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</DRUG>": 768,
|
| 3 |
+
"</FRAG>": 770,
|
| 4 |
+
"<DRUG>": 767,
|
| 5 |
+
"<EOS_FRAG>": 771,
|
| 6 |
+
"<FRAG>": 769
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "best_model_checkpoint",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.33.3",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 767
|
| 27 |
+
}
|
errors_25-11-30-16-19-43.txt
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[train]
|
| 2 |
+
unclosed ring: 0
|
| 3 |
+
duplicated ring closure: 0
|
| 4 |
+
extra close parentheses: 0
|
| 5 |
+
extra open parentheses: 0
|
| 6 |
+
non-ring atom: 0
|
| 7 |
+
can't kekulize: 0
|
| 8 |
+
other: 0
|
| 9 |
+
|
| 10 |
+
[val]
|
| 11 |
+
unclosed ring: 0
|
| 12 |
+
duplicated ring closure: 0
|
| 13 |
+
extra close parentheses: 0
|
| 14 |
+
extra open parentheses: 0
|
| 15 |
+
non-ring atom: 0
|
| 16 |
+
can't kekulize: 0
|
| 17 |
+
other: 0
|
| 18 |
+
|
| 19 |
+
[test]
|
| 20 |
+
unclosed ring: 0
|
| 21 |
+
duplicated ring closure: 0
|
| 22 |
+
extra close parentheses: 0
|
| 23 |
+
extra open parentheses: 0
|
| 24 |
+
non-ring atom: 0
|
| 25 |
+
can't kekulize: 0
|
| 26 |
+
other: 0
|
| 27 |
+
|
merges.txt
ADDED
|
@@ -0,0 +1,507 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
+
) )
|
| 3 |
+
c c
|
| 4 |
+
)) ))
|
| 5 |
+
C C
|
| 6 |
+
cc cc
|
| 7 |
+
č Ċ
|
| 8 |
+
)))) ))))
|
| 9 |
+
N C
|
| 10 |
+
)))) ))
|
| 11 |
+
CC C
|
| 12 |
+
@ @
|
| 13 |
+
cccc cc
|
| 14 |
+
c n
|
| 15 |
+
+ ]
|
| 16 |
+
) [
|
| 17 |
+
cc c
|
| 18 |
+
N CC
|
| 19 |
+
N H
|
| 20 |
+
C O
|
| 21 |
+
)))))) )
|
| 22 |
+
c C
|
| 23 |
+
)))))))) ))
|
| 24 |
+
) =
|
| 25 |
+
cccc C
|
| 26 |
+
n c
|
| 27 |
+
CC CC
|
| 28 |
+
O C
|
| 29 |
+
)))))))) )
|
| 30 |
+
)))) )
|
| 31 |
+
- ]
|
| 32 |
+
C cccc
|
| 33 |
+
1 0
|
| 34 |
+
n H
|
| 35 |
+
C NC
|
| 36 |
+
C l
|
| 37 |
+
cccc c
|
| 38 |
+
O CC
|
| 39 |
+
n n
|
| 40 |
+
)))))))))) )
|
| 41 |
+
)) )
|
| 42 |
+
N CCC
|
| 43 |
+
cn c
|
| 44 |
+
N cccc
|
| 45 |
+
ccccC l
|
| 46 |
+
CC O
|
| 47 |
+
C N
|
| 48 |
+
)))))))) ))))
|
| 49 |
+
B r
|
| 50 |
+
ccc C
|
| 51 |
+
C cccccc
|
| 52 |
+
cn cc
|
| 53 |
+
n cc
|
| 54 |
+
CC NC
|
| 55 |
+
+] =
|
| 56 |
+
CO cccc
|
| 57 |
+
C S
|
| 58 |
+
-] ))
|
| 59 |
+
cccc F
|
| 60 |
+
C cc
|
| 61 |
+
] [
|
| 62 |
+
s c
|
| 63 |
+
cn n
|
| 64 |
+
N cccccc
|
| 65 |
+
CO C
|
| 66 |
+
+] [
|
| 67 |
+
CC CCC
|
| 68 |
+
cC l
|
| 69 |
+
@ ]
|
| 70 |
+
NCC CC
|
| 71 |
+
C ccc
|
| 72 |
+
)))))))) )))))
|
| 73 |
+
6 9
|
| 74 |
+
S C
|
| 75 |
+
@@ ]
|
| 76 |
+
CCC NC
|
| 77 |
+
cc C
|
| 78 |
+
CCC O
|
| 79 |
+
C NCC
|
| 80 |
+
CC OC
|
| 81 |
+
cn nc
|
| 82 |
+
o c
|
| 83 |
+
CO cccccc
|
| 84 |
+
c s
|
| 85 |
+
cccc s
|
| 86 |
+
CC S
|
| 87 |
+
C cn
|
| 88 |
+
NCC NC
|
| 89 |
+
cc n
|
| 90 |
+
)))))))) ))))))
|
| 91 |
+
10 6
|
| 92 |
+
cccc nc
|
| 93 |
+
C ccccC
|
| 94 |
+
CCC N
|
| 95 |
+
9 6
|
| 96 |
+
CC N
|
| 97 |
+
Ccccc c
|
| 98 |
+
NCC OCC
|
| 99 |
+
cccc NC
|
| 100 |
+
cccc o
|
| 101 |
+
-] )
|
| 102 |
+
C cccC
|
| 103 |
+
c F
|
| 104 |
+
cccc cC
|
| 105 |
+
n o
|
| 106 |
+
cn cccccc
|
| 107 |
+
) /
|
| 108 |
+
CCCC CC
|
| 109 |
+
cccc cn
|
| 110 |
+
NCC CCC
|
| 111 |
+
S CC
|
| 112 |
+
C F
|
| 113 |
+
cn cC
|
| 114 |
+
ccccc F
|
| 115 |
+
CO ccccC
|
| 116 |
+
)))))) [
|
| 117 |
+
ccc Cl
|
| 118 |
+
N S
|
| 119 |
+
ccc F
|
| 120 |
+
cc cncc
|
| 121 |
+
n nc
|
| 122 |
+
)))))))) )))))))
|
| 123 |
+
N NC
|
| 124 |
+
ccccc NC
|
| 125 |
+
CC NCC
|
| 126 |
+
CC cccccc
|
| 127 |
+
NC cccccc
|
| 128 |
+
N ccccC
|
| 129 |
+
n cC
|
| 130 |
+
)))))) )[
|
| 131 |
+
cccc Br
|
| 132 |
+
C cnc
|
| 133 |
+
Ccccc NC
|
| 134 |
+
)) [
|
| 135 |
+
O CO
|
| 136 |
+
Ncccc F
|
| 137 |
+
n cn
|
| 138 |
+
n C
|
| 139 |
+
9 5
|
| 140 |
+
cccc cCl
|
| 141 |
+
cc F
|
| 142 |
+
+] )
|
| 143 |
+
= [
|
| 144 |
+
cccc OC
|
| 145 |
+
cc nn
|
| 146 |
+
OCC O
|
| 147 |
+
O cccccc
|
| 148 |
+
C ncc
|
| 149 |
+
CO ccc
|
| 150 |
+
c OC
|
| 151 |
+
N ccccc
|
| 152 |
+
1 3
|
| 153 |
+
] %
|
| 154 |
+
o cC
|
| 155 |
+
Ncccc cC
|
| 156 |
+
C cnn
|
| 157 |
+
Ccccc cC
|
| 158 |
+
c NC
|
| 159 |
+
NCC O
|
| 160 |
+
)))))))) [
|
| 161 |
+
cncc s
|
| 162 |
+
n cccccc
|
| 163 |
+
ccc sc
|
| 164 |
+
CO CC
|
| 165 |
+
N cn
|
| 166 |
+
NCC CCCC
|
| 167 |
+
CO ccccc
|
| 168 |
+
cc Cl
|
| 169 |
+
C NCCC
|
| 170 |
+
CCO cccccc
|
| 171 |
+
cc ncc
|
| 172 |
+
N ccccCl
|
| 173 |
+
C c
|
| 174 |
+
)))))))) ))))))))
|
| 175 |
+
o n
|
| 176 |
+
cccc O
|
| 177 |
+
N N
|
| 178 |
+
Ccccc F
|
| 179 |
+
COcccc NC
|
| 180 |
+
nn cC
|
| 181 |
+
cc nc
|
| 182 |
+
1 1
|
| 183 |
+
N ccc
|
| 184 |
+
NCC cccccc
|
| 185 |
+
cc sc
|
| 186 |
+
cn cccc
|
| 187 |
+
CCCC NC
|
| 188 |
+
cccc S
|
| 189 |
+
CC OCC
|
| 190 |
+
Ccc C
|
| 191 |
+
C n
|
| 192 |
+
ccc NC
|
| 193 |
+
cs ccc
|
| 194 |
+
)))))))) )[
|
| 195 |
+
NCC N
|
| 196 |
+
C nc
|
| 197 |
+
COcccc cC
|
| 198 |
+
ncc cn
|
| 199 |
+
cccc cccc
|
| 200 |
+
nn n
|
| 201 |
+
CC nc
|
| 202 |
+
C ccccCl
|
| 203 |
+
+] ))
|
| 204 |
+
cc cn
|
| 205 |
+
Ccn cC
|
| 206 |
+
N cccC
|
| 207 |
+
OC F
|
| 208 |
+
C Ncccc
|
| 209 |
+
cc s
|
| 210 |
+
CCCC N
|
| 211 |
+
cnn C
|
| 212 |
+
)))))))) )))))))))
|
| 213 |
+
CS C
|
| 214 |
+
CO cccC
|
| 215 |
+
Ccc sc
|
| 216 |
+
CN cccccc
|
| 217 |
+
Cccc NC
|
| 218 |
+
CCO cccc
|
| 219 |
+
Cccccc NC
|
| 220 |
+
cnn cn
|
| 221 |
+
cn oc
|
| 222 |
+
ncc nc
|
| 223 |
+
C nn
|
| 224 |
+
Ccccc S
|
| 225 |
+
)))))))))) [
|
| 226 |
+
Ncccc cCl
|
| 227 |
+
)))) )[
|
| 228 |
+
CC cccc
|
| 229 |
+
c o
|
| 230 |
+
Ccccc nc
|
| 231 |
+
cncc cn
|
| 232 |
+
ncn cn
|
| 233 |
+
5 9
|
| 234 |
+
)) )[
|
| 235 |
+
ccc Br
|
| 236 |
+
N cnc
|
| 237 |
+
CC SC
|
| 238 |
+
cc cnc
|
| 239 |
+
CN S
|
| 240 |
+
CCC S
|
| 241 |
+
Ccn ocC
|
| 242 |
+
CCC cccccc
|
| 243 |
+
ccccc Br
|
| 244 |
+
cccc ccccc
|
| 245 |
+
cnn cC
|
| 246 |
+
@@] =
|
| 247 |
+
ccnn C
|
| 248 |
+
cn cnc
|
| 249 |
+
NCCC NC
|
| 250 |
+
CC l
|
| 251 |
+
CCC OCC
|
| 252 |
+
cc OC
|
| 253 |
+
Cccc F
|
| 254 |
+
NCC OC
|
| 255 |
+
Ccccc s
|
| 256 |
+
ccccC NC
|
| 257 |
+
)))) [
|
| 258 |
+
N cc
|
| 259 |
+
)) =
|
| 260 |
+
CCCC CCC
|
| 261 |
+
CNC cccccc
|
| 262 |
+
n cccc
|
| 263 |
+
CC ncc
|
| 264 |
+
c S
|
| 265 |
+
ccccC F
|
| 266 |
+
cncc n
|
| 267 |
+
cc NC
|
| 268 |
+
n cnc
|
| 269 |
+
Ncccc NC
|
| 270 |
+
CCCC O
|
| 271 |
+
ccccc OC
|
| 272 |
+
CCCN S
|
| 273 |
+
/ [
|
| 274 |
+
c O
|
| 275 |
+
c Br
|
| 276 |
+
CC cnnC
|
| 277 |
+
ccc OC
|
| 278 |
+
N ccC
|
| 279 |
+
NC cccc
|
| 280 |
+
cn ocC
|
| 281 |
+
ccc oc
|
| 282 |
+
cccccC F
|
| 283 |
+
COcccc OC
|
| 284 |
+
Ccccc O
|
| 285 |
+
cncc C
|
| 286 |
+
-] )))
|
| 287 |
+
CO ccccCl
|
| 288 |
+
-] )[
|
| 289 |
+
cccc CC
|
| 290 |
+
c N
|
| 291 |
+
cc Br
|
| 292 |
+
NC cccco
|
| 293 |
+
1 4
|
| 294 |
+
cn nnn
|
| 295 |
+
nn C
|
| 296 |
+
Ccccc o
|
| 297 |
+
OCC F
|
| 298 |
+
cnnc NC
|
| 299 |
+
c sc
|
| 300 |
+
o cccccc
|
| 301 |
+
s cC
|
| 302 |
+
CNCC NC
|
| 303 |
+
-] )=
|
| 304 |
+
@] =
|
| 305 |
+
Ccnn C
|
| 306 |
+
N cccCl
|
| 307 |
+
s cc
|
| 308 |
+
OC cccccc
|
| 309 |
+
CO CCNC
|
| 310 |
+
Cccc sc
|
| 311 |
+
n CC
|
| 312 |
+
NC ccccC
|
| 313 |
+
1 2
|
| 314 |
+
cn cn
|
| 315 |
+
ccc S
|
| 316 |
+
)))))))))) )[
|
| 317 |
+
CC n
|
| 318 |
+
N cnnc
|
| 319 |
+
COcccc F
|
| 320 |
+
NCC Ncccccc
|
| 321 |
+
Ccc nc
|
| 322 |
+
CS CC
|
| 323 |
+
8 5
|
| 324 |
+
S cccccc
|
| 325 |
+
CccccC NC
|
| 326 |
+
s ccc
|
| 327 |
+
CS cccccc
|
| 328 |
+
COccccC NC
|
| 329 |
+
Cccc Cl
|
| 330 |
+
Ncccc S
|
| 331 |
+
Ncccc Br
|
| 332 |
+
NC ccccF
|
| 333 |
+
cccc cccccc
|
| 334 |
+
n oc
|
| 335 |
+
-] ))))))))
|
| 336 |
+
ccncc n
|
| 337 |
+
CC Ncccccc
|
| 338 |
+
NCC NS
|
| 339 |
+
CCO ccccNC
|
| 340 |
+
C NCCCC
|
| 341 |
+
O CCC
|
| 342 |
+
cccc N
|
| 343 |
+
CNCC OCC
|
| 344 |
+
Ncccc nc
|
| 345 |
+
COcccc S
|
| 346 |
+
C cnnc
|
| 347 |
+
ncc C
|
| 348 |
+
CS cnnc
|
| 349 |
+
ccn C
|
| 350 |
+
O ccccC
|
| 351 |
+
CNCC O
|
| 352 |
+
)))))))) ))))))))))
|
| 353 |
+
NCC NCC
|
| 354 |
+
Cccccc F
|
| 355 |
+
CC F
|
| 356 |
+
CCO ccccC
|
| 357 |
+
S cnnc
|
| 358 |
+
Ccccc cn
|
| 359 |
+
N cnccs
|
| 360 |
+
ccccc S
|
| 361 |
+
CC cnc
|
| 362 |
+
nn nnc
|
| 363 |
+
-] )))))))))
|
| 364 |
+
-])) [
|
| 365 |
+
Ccn oc
|
| 366 |
+
o ccc
|
| 367 |
+
CC cn
|
| 368 |
+
CCCC CCCC
|
| 369 |
+
-] ))))
|
| 370 |
+
O CCCC
|
| 371 |
+
nn ccc
|
| 372 |
+
O CCCO
|
| 373 |
+
cccccc c
|
| 374 |
+
CCN S
|
| 375 |
+
NC ccccnc
|
| 376 |
+
-] ))))))))))
|
| 377 |
+
Ccc cncc
|
| 378 |
+
cccC F
|
| 379 |
+
ncn nn
|
| 380 |
+
N cccccF
|
| 381 |
+
cccc n
|
| 382 |
+
Ccc F
|
| 383 |
+
Cncc C
|
| 384 |
+
n cnnc
|
| 385 |
+
NCC F
|
| 386 |
+
ccccc O
|
| 387 |
+
ccsc NC
|
| 388 |
+
cccc OCC
|
| 389 |
+
5 8
|
| 390 |
+
\ [
|
| 391 |
+
COccc OC
|
| 392 |
+
Ccc n
|
| 393 |
+
cccc SC
|
| 394 |
+
NCCC O
|
| 395 |
+
Ccccc OC
|
| 396 |
+
nc N
|
| 397 |
+
)))))))))))) [
|
| 398 |
+
c CC
|
| 399 |
+
COcccc CC
|
| 400 |
+
CO cccccNC
|
| 401 |
+
Ncccc OC
|
| 402 |
+
Ccn cccccc
|
| 403 |
+
N cccccNC
|
| 404 |
+
cnc CC
|
| 405 |
+
cc cnn
|
| 406 |
+
cnc CCC
|
| 407 |
+
N cccF
|
| 408 |
+
CC nncC
|
| 409 |
+
NCC S
|
| 410 |
+
Ccccc cCl
|
| 411 |
+
CCC OC
|
| 412 |
+
CC ccC
|
| 413 |
+
cn ccc
|
| 414 |
+
NCC CCCCC
|
| 415 |
+
)))))) =
|
| 416 |
+
+] )[
|
| 417 |
+
Ccc Cl
|
| 418 |
+
cc O
|
| 419 |
+
cc N
|
| 420 |
+
)))))))) )))))))))))
|
| 421 |
+
NC N
|
| 422 |
+
CC ccccC
|
| 423 |
+
OCC CCC
|
| 424 |
+
Ccc cnc
|
| 425 |
+
Ncn cnc
|
| 426 |
+
Ccccc Br
|
| 427 |
+
ccccOC F
|
| 428 |
+
CO CCCNC
|
| 429 |
+
Ccccc CC
|
| 430 |
+
nc SCC
|
| 431 |
+
F CF
|
| 432 |
+
C cncc
|
| 433 |
+
o nc
|
| 434 |
+
CC NCCC
|
| 435 |
+
Ncccc CC
|
| 436 |
+
O ccccCl
|
| 437 |
+
Cccc Br
|
| 438 |
+
O cccc
|
| 439 |
+
CO CCO
|
| 440 |
+
NcccccC F
|
| 441 |
+
N ccnn
|
| 442 |
+
Ccc cn
|
| 443 |
+
n ccc
|
| 444 |
+
CC nn
|
| 445 |
+
NC ccccCl
|
| 446 |
+
NC ccccs
|
| 447 |
+
N cncC
|
| 448 |
+
CCC SCC
|
| 449 |
+
+] %
|
| 450 |
+
C nnc
|
| 451 |
+
N cncc
|
| 452 |
+
Ccc nn
|
| 453 |
+
ccs cC
|
| 454 |
+
cccc NCC
|
| 455 |
+
ccn cC
|
| 456 |
+
CO CCC
|
| 457 |
+
CCCCC NC
|
| 458 |
+
C ncC
|
| 459 |
+
Ncc cnn
|
| 460 |
+
N O
|
| 461 |
+
CC ccc
|
| 462 |
+
)= [
|
| 463 |
+
Ccc scC
|
| 464 |
+
N ccn
|
| 465 |
+
cn cncc
|
| 466 |
+
CO CCN
|
| 467 |
+
cs cC
|
| 468 |
+
Ncn cccc
|
| 469 |
+
Ccccc OCC
|
| 470 |
+
Cncc nc
|
| 471 |
+
CC ncC
|
| 472 |
+
cn cnn
|
| 473 |
+
NCCC cccccc
|
| 474 |
+
cn nn
|
| 475 |
+
Cccccc O
|
| 476 |
+
CC NCCNC
|
| 477 |
+
N SC
|
| 478 |
+
COcccc Br
|
| 479 |
+
O ccccF
|
| 480 |
+
CCNC cccccc
|
| 481 |
+
cs cnc
|
| 482 |
+
cC F
|
| 483 |
+
nc S
|
| 484 |
+
Ccc ncc
|
| 485 |
+
Cncc cn
|
| 486 |
+
N csccc
|
| 487 |
+
CC ccccNC
|
| 488 |
+
NC cccccn
|
| 489 |
+
)))))))))))) )[
|
| 490 |
+
cnn cccccn
|
| 491 |
+
cnnc SCC
|
| 492 |
+
NCC cc
|
| 493 |
+
NC ccc
|
| 494 |
+
CC cncC
|
| 495 |
+
NCC CCCCCC
|
| 496 |
+
COcccccC NC
|
| 497 |
+
Cnn ccc
|
| 498 |
+
CC ccccF
|
| 499 |
+
NCC Ncccc
|
| 500 |
+
CCO ccc
|
| 501 |
+
sc NC
|
| 502 |
+
NCCNC cccccc
|
| 503 |
+
C cnccn
|
| 504 |
+
CCO ccccc
|
| 505 |
+
ccs cc
|
| 506 |
+
n cncccccc
|
| 507 |
+
cnc NC
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae53f7ee1525c54057edc09fb9a1d796ad986cccc7ae962e9e5a86db6c04cd11
|
| 3 |
+
size 176461682
|
run_args.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_epochs": 20,
|
| 3 |
+
"batch_size": 16,
|
| 4 |
+
"max_length": 96,
|
| 5 |
+
"seq_penalty": 0.7448832409704772,
|
| 6 |
+
"invalid_smiles_penalty": 14.87225684138008,
|
| 7 |
+
"time": "25-11-30-16-19-43",
|
| 8 |
+
"representation": "DeepSMILES"
|
| 9 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<pad>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<mask>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<unk>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": {
|
| 46 |
+
"__type": "AddedToken",
|
| 47 |
+
"content": "<s>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
},
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"cls_token": {
|
| 55 |
+
"__type": "AddedToken",
|
| 56 |
+
"content": "<s>",
|
| 57 |
+
"lstrip": false,
|
| 58 |
+
"normalized": true,
|
| 59 |
+
"rstrip": false,
|
| 60 |
+
"single_word": false
|
| 61 |
+
},
|
| 62 |
+
"eos_token": {
|
| 63 |
+
"__type": "AddedToken",
|
| 64 |
+
"content": "</s>",
|
| 65 |
+
"lstrip": false,
|
| 66 |
+
"normalized": true,
|
| 67 |
+
"rstrip": false,
|
| 68 |
+
"single_word": false
|
| 69 |
+
},
|
| 70 |
+
"errors": "replace",
|
| 71 |
+
"mask_token": {
|
| 72 |
+
"__type": "AddedToken",
|
| 73 |
+
"content": "<mask>",
|
| 74 |
+
"lstrip": true,
|
| 75 |
+
"normalized": true,
|
| 76 |
+
"rstrip": false,
|
| 77 |
+
"single_word": false
|
| 78 |
+
},
|
| 79 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 80 |
+
"pad_token": {
|
| 81 |
+
"__type": "AddedToken",
|
| 82 |
+
"content": "<pad>",
|
| 83 |
+
"lstrip": false,
|
| 84 |
+
"normalized": true,
|
| 85 |
+
"rstrip": false,
|
| 86 |
+
"single_word": false
|
| 87 |
+
},
|
| 88 |
+
"sep_token": {
|
| 89 |
+
"__type": "AddedToken",
|
| 90 |
+
"content": "</s>",
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"normalized": true,
|
| 93 |
+
"rstrip": false,
|
| 94 |
+
"single_word": false
|
| 95 |
+
},
|
| 96 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 97 |
+
"trim_offsets": true,
|
| 98 |
+
"unk_token": {
|
| 99 |
+
"__type": "AddedToken",
|
| 100 |
+
"content": "<unk>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false
|
| 105 |
+
}
|
| 106 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,769 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"!": 5,
|
| 3 |
+
"\"": 6,
|
| 4 |
+
"#": 7,
|
| 5 |
+
"$": 8,
|
| 6 |
+
"%": 9,
|
| 7 |
+
"&": 10,
|
| 8 |
+
"'": 11,
|
| 9 |
+
"(": 12,
|
| 10 |
+
")": 13,
|
| 11 |
+
"))": 261,
|
| 12 |
+
")))": 300,
|
| 13 |
+
"))))": 263,
|
| 14 |
+
")))))": 289,
|
| 15 |
+
"))))))": 269,
|
| 16 |
+
")))))))": 280,
|
| 17 |
+
"))))))))": 267,
|
| 18 |
+
")))))))))": 288,
|
| 19 |
+
"))))))))))": 282,
|
| 20 |
+
")))))))))))": 299,
|
| 21 |
+
"))))))))))))": 307,
|
| 22 |
+
")))))))))))))": 331,
|
| 23 |
+
"))))))))))))))": 349,
|
| 24 |
+
")))))))))))))))": 381,
|
| 25 |
+
"))))))))))))))))": 433,
|
| 26 |
+
")))))))))))))))))": 471,
|
| 27 |
+
"))))))))))))))))))": 611,
|
| 28 |
+
")))))))))))))))))))": 679,
|
| 29 |
+
")))))))))))))[": 748,
|
| 30 |
+
"))))))))))))[": 656,
|
| 31 |
+
")))))))))))[": 575,
|
| 32 |
+
"))))))))))[": 484,
|
| 33 |
+
")))))))))[": 453,
|
| 34 |
+
"))))))))[": 419,
|
| 35 |
+
")))))))[": 389,
|
| 36 |
+
"))))))=": 674,
|
| 37 |
+
"))))))[": 375,
|
| 38 |
+
")))))[": 486,
|
| 39 |
+
"))))[": 516,
|
| 40 |
+
")))[": 493,
|
| 41 |
+
"))=": 518,
|
| 42 |
+
"))[": 393,
|
| 43 |
+
")/": 366,
|
| 44 |
+
")=": 283,
|
| 45 |
+
")=[": 721,
|
| 46 |
+
")[": 275,
|
| 47 |
+
"*": 14,
|
| 48 |
+
"+": 15,
|
| 49 |
+
"+]": 274,
|
| 50 |
+
"+]%": 708,
|
| 51 |
+
"+])": 401,
|
| 52 |
+
"+]))": 462,
|
| 53 |
+
"+])[": 675,
|
| 54 |
+
"+]=": 314,
|
| 55 |
+
"+][": 325,
|
| 56 |
+
",": 16,
|
| 57 |
+
"-": 17,
|
| 58 |
+
"-]": 290,
|
| 59 |
+
"-])": 360,
|
| 60 |
+
"-]))": 317,
|
| 61 |
+
"-])))": 545,
|
| 62 |
+
"-]))))": 628,
|
| 63 |
+
"-]))))))))": 594,
|
| 64 |
+
"-])))))))))": 622,
|
| 65 |
+
"-]))))))))))": 635,
|
| 66 |
+
"-]))[": 623,
|
| 67 |
+
"-])=": 562,
|
| 68 |
+
"-])[": 547,
|
| 69 |
+
".": 18,
|
| 70 |
+
"/": 19,
|
| 71 |
+
"/[": 532,
|
| 72 |
+
"0": 20,
|
| 73 |
+
"1": 21,
|
| 74 |
+
"10": 292,
|
| 75 |
+
"106": 350,
|
| 76 |
+
"11": 441,
|
| 77 |
+
"12": 572,
|
| 78 |
+
"13": 411,
|
| 79 |
+
"14": 552,
|
| 80 |
+
"2": 22,
|
| 81 |
+
"3": 23,
|
| 82 |
+
"4": 24,
|
| 83 |
+
"5": 25,
|
| 84 |
+
"58": 648,
|
| 85 |
+
"59": 492,
|
| 86 |
+
"6": 26,
|
| 87 |
+
"69": 332,
|
| 88 |
+
"7": 27,
|
| 89 |
+
"8": 28,
|
| 90 |
+
"85": 582,
|
| 91 |
+
"9": 29,
|
| 92 |
+
"95": 398,
|
| 93 |
+
"96": 354,
|
| 94 |
+
":": 30,
|
| 95 |
+
";": 31,
|
| 96 |
+
"<": 32,
|
| 97 |
+
"</s>": 1,
|
| 98 |
+
"<mask>": 3,
|
| 99 |
+
"<pad>": 2,
|
| 100 |
+
"<s>": 0,
|
| 101 |
+
"<unk>": 4,
|
| 102 |
+
"=": 33,
|
| 103 |
+
"=[": 402,
|
| 104 |
+
">": 34,
|
| 105 |
+
"?": 35,
|
| 106 |
+
"@": 36,
|
| 107 |
+
"@@": 271,
|
| 108 |
+
"@@]": 334,
|
| 109 |
+
"@@]=": 505,
|
| 110 |
+
"@]": 328,
|
| 111 |
+
"@]=": 563,
|
| 112 |
+
"A": 37,
|
| 113 |
+
"B": 38,
|
| 114 |
+
"Br": 308,
|
| 115 |
+
"C": 39,
|
| 116 |
+
"CC": 264,
|
| 117 |
+
"CCC": 270,
|
| 118 |
+
"CCCC": 286,
|
| 119 |
+
"CCCCC": 326,
|
| 120 |
+
"CCCCCC": 367,
|
| 121 |
+
"CCCCCCC": 519,
|
| 122 |
+
"CCCCCCCC": 627,
|
| 123 |
+
"CCCCCNC": 716,
|
| 124 |
+
"CCCCN": 469,
|
| 125 |
+
"CCCCNC": 446,
|
| 126 |
+
"CCCCO": 529,
|
| 127 |
+
"CCCN": 353,
|
| 128 |
+
"CCCNC": 335,
|
| 129 |
+
"CCCNS": 531,
|
| 130 |
+
"CCCO": 337,
|
| 131 |
+
"CCCOC": 670,
|
| 132 |
+
"CCCOCC": 510,
|
| 133 |
+
"CCCS": 499,
|
| 134 |
+
"CCCSCC": 707,
|
| 135 |
+
"CCCcccccc": 501,
|
| 136 |
+
"CCF": 614,
|
| 137 |
+
"CCN": 355,
|
| 138 |
+
"CCNC": 313,
|
| 139 |
+
"CCNCC": 384,
|
| 140 |
+
"CCNCCC": 693,
|
| 141 |
+
"CCNCCNC": 735,
|
| 142 |
+
"CCNCcccccc": 739,
|
| 143 |
+
"CCNS": 633,
|
| 144 |
+
"CCNcccccc": 596,
|
| 145 |
+
"CCO": 305,
|
| 146 |
+
"CCOC": 339,
|
| 147 |
+
"CCOCC": 448,
|
| 148 |
+
"CCOccc": 759,
|
| 149 |
+
"CCOcccc": 477,
|
| 150 |
+
"CCOccccC": 615,
|
| 151 |
+
"CCOccccNC": 598,
|
| 152 |
+
"CCOccccc": 763,
|
| 153 |
+
"CCOcccccc": 429,
|
| 154 |
+
"CCS": 345,
|
| 155 |
+
"CCSC": 496,
|
| 156 |
+
"CCccC": 671,
|
| 157 |
+
"CCccc": 720,
|
| 158 |
+
"CCcccc": 487,
|
| 159 |
+
"CCccccC": 681,
|
| 160 |
+
"CCccccF": 757,
|
| 161 |
+
"CCccccNC": 746,
|
| 162 |
+
"CCcccccc": 385,
|
| 163 |
+
"CCcn": 626,
|
| 164 |
+
"CCcnc": 620,
|
| 165 |
+
"CCcncC": 753,
|
| 166 |
+
"CCcnnC": 535,
|
| 167 |
+
"CCl": 509,
|
| 168 |
+
"CCn": 576,
|
| 169 |
+
"CCnc": 460,
|
| 170 |
+
"CCncC": 730,
|
| 171 |
+
"CCncc": 522,
|
| 172 |
+
"CCnn": 703,
|
| 173 |
+
"CCnncC": 667,
|
| 174 |
+
"CF": 371,
|
| 175 |
+
"CN": 306,
|
| 176 |
+
"CNC": 294,
|
| 177 |
+
"CNCC": 338,
|
| 178 |
+
"CNCCC": 428,
|
| 179 |
+
"CNCCCC": 599,
|
| 180 |
+
"CNCCNC": 561,
|
| 181 |
+
"CNCCO": 610,
|
| 182 |
+
"CNCCOCC": 602,
|
| 183 |
+
"CNCcccccc": 520,
|
| 184 |
+
"CNS": 498,
|
| 185 |
+
"CNcccc": 467,
|
| 186 |
+
"CNcccccc": 475,
|
| 187 |
+
"CO": 279,
|
| 188 |
+
"COC": 324,
|
| 189 |
+
"COCC": 423,
|
| 190 |
+
"COCCC": 715,
|
| 191 |
+
"COCCCNC": 687,
|
| 192 |
+
"COCCN": 725,
|
| 193 |
+
"COCCNC": 568,
|
| 194 |
+
"COCCO": 698,
|
| 195 |
+
"COccc": 408,
|
| 196 |
+
"COcccC": 473,
|
| 197 |
+
"COcccOC": 650,
|
| 198 |
+
"COcccc": 315,
|
| 199 |
+
"COccccBr": 737,
|
| 200 |
+
"COccccC": 374,
|
| 201 |
+
"COccccCC": 658,
|
| 202 |
+
"COccccCNC": 587,
|
| 203 |
+
"COccccCl": 546,
|
| 204 |
+
"COccccF": 578,
|
| 205 |
+
"COccccNC": 438,
|
| 206 |
+
"COccccOC": 542,
|
| 207 |
+
"COccccS": 604,
|
| 208 |
+
"COccccc": 426,
|
| 209 |
+
"COcccccC": 456,
|
| 210 |
+
"COcccccCNC": 755,
|
| 211 |
+
"COcccccNC": 659,
|
| 212 |
+
"COcccccc": 342,
|
| 213 |
+
"CS": 316,
|
| 214 |
+
"CSC": 472,
|
| 215 |
+
"CSCC": 581,
|
| 216 |
+
"CScccccc": 586,
|
| 217 |
+
"CScnnc": 607,
|
| 218 |
+
"Cc": 432,
|
| 219 |
+
"Ccc": 319,
|
| 220 |
+
"CccC": 449,
|
| 221 |
+
"CccCl": 676,
|
| 222 |
+
"CccF": 641,
|
| 223 |
+
"Cccc": 330,
|
| 224 |
+
"CcccBr": 696,
|
| 225 |
+
"CcccC": 361,
|
| 226 |
+
"CcccCl": 588,
|
| 227 |
+
"CcccF": 512,
|
| 228 |
+
"CcccNC": 476,
|
| 229 |
+
"Ccccc": 291,
|
| 230 |
+
"CccccBr": 685,
|
| 231 |
+
"CccccC": 352,
|
| 232 |
+
"CccccCC": 688,
|
| 233 |
+
"CccccCNC": 584,
|
| 234 |
+
"CccccCl": 461,
|
| 235 |
+
"CccccF": 437,
|
| 236 |
+
"CccccNC": 392,
|
| 237 |
+
"CccccO": 543,
|
| 238 |
+
"CccccOC": 654,
|
| 239 |
+
"CccccOCC": 728,
|
| 240 |
+
"CccccS": 483,
|
| 241 |
+
"Cccccc": 356,
|
| 242 |
+
"CcccccC": 416,
|
| 243 |
+
"CcccccCl": 669,
|
| 244 |
+
"CcccccF": 613,
|
| 245 |
+
"CcccccNC": 478,
|
| 246 |
+
"CcccccO": 734,
|
| 247 |
+
"Ccccccc": 310,
|
| 248 |
+
"Ccccccn": 617,
|
| 249 |
+
"Cccccnc": 489,
|
| 250 |
+
"Ccccco": 555,
|
| 251 |
+
"Cccccs": 514,
|
| 252 |
+
"Ccccn": 701,
|
| 253 |
+
"Ccccnc": 683,
|
| 254 |
+
"Ccccncc": 636,
|
| 255 |
+
"Ccccsc": 569,
|
| 256 |
+
"Cccn": 651,
|
| 257 |
+
"Cccnc": 580,
|
| 258 |
+
"Cccncc": 743,
|
| 259 |
+
"Cccnn": 711,
|
| 260 |
+
"Cccsc": 474,
|
| 261 |
+
"CccscC": 722,
|
| 262 |
+
"Ccn": 346,
|
| 263 |
+
"Ccnc": 391,
|
| 264 |
+
"CcncC": 464,
|
| 265 |
+
"Ccncc": 691,
|
| 266 |
+
"Ccncccccc": 661,
|
| 267 |
+
"Ccnccn": 762,
|
| 268 |
+
"Ccnn": 415,
|
| 269 |
+
"CcnnC": 564,
|
| 270 |
+
"Ccnnc": 605,
|
| 271 |
+
"Ccnoc": 624,
|
| 272 |
+
"CcnocC": 500,
|
| 273 |
+
"Cl": 295,
|
| 274 |
+
"Cn": 450,
|
| 275 |
+
"Cnc": 455,
|
| 276 |
+
"CncC": 717,
|
| 277 |
+
"Cncc": 407,
|
| 278 |
+
"CnccC": 642,
|
| 279 |
+
"Cncccn": 744,
|
| 280 |
+
"Cnccnc": 729,
|
| 281 |
+
"Cnn": 482,
|
| 282 |
+
"Cnnc": 709,
|
| 283 |
+
"Cnnccc": 756,
|
| 284 |
+
"D": 40,
|
| 285 |
+
"E": 41,
|
| 286 |
+
"F": 42,
|
| 287 |
+
"FCF": 690,
|
| 288 |
+
"G": 43,
|
| 289 |
+
"H": 44,
|
| 290 |
+
"I": 45,
|
| 291 |
+
"J": 46,
|
| 292 |
+
"K": 47,
|
| 293 |
+
"L": 48,
|
| 294 |
+
"M": 49,
|
| 295 |
+
"N": 50,
|
| 296 |
+
"NC": 268,
|
| 297 |
+
"NCC": 277,
|
| 298 |
+
"NCCC": 301,
|
| 299 |
+
"NCCCC": 329,
|
| 300 |
+
"NCCCCC": 369,
|
| 301 |
+
"NCCCCCC": 425,
|
| 302 |
+
"NCCCCCCC": 673,
|
| 303 |
+
"NCCCCCCCC": 754,
|
| 304 |
+
"NCCCNC": 508,
|
| 305 |
+
"NCCCO": 653,
|
| 306 |
+
"NCCCcccccc": 732,
|
| 307 |
+
"NCCF": 644,
|
| 308 |
+
"NCCN": 454,
|
| 309 |
+
"NCCNC": 347,
|
| 310 |
+
"NCCNCC": 612,
|
| 311 |
+
"NCCNCcccccc": 761,
|
| 312 |
+
"NCCNS": 597,
|
| 313 |
+
"NCCNcccc": 758,
|
| 314 |
+
"NCCNcccccc": 579,
|
| 315 |
+
"NCCO": 418,
|
| 316 |
+
"NCCOC": 513,
|
| 317 |
+
"NCCOCC": 357,
|
| 318 |
+
"NCCS": 668,
|
| 319 |
+
"NCCcc": 751,
|
| 320 |
+
"NCCcccccc": 443,
|
| 321 |
+
"NCN": 680,
|
| 322 |
+
"NCccc": 752,
|
| 323 |
+
"NCcccc": 538,
|
| 324 |
+
"NCccccC": 571,
|
| 325 |
+
"NCccccCl": 704,
|
| 326 |
+
"NCccccF": 591,
|
| 327 |
+
"NCcccccc": 386,
|
| 328 |
+
"NCcccccn": 747,
|
| 329 |
+
"NCccccnc": 634,
|
| 330 |
+
"NCcccco": 551,
|
| 331 |
+
"NCccccs": 705,
|
| 332 |
+
"NH": 278,
|
| 333 |
+
"NN": 436,
|
| 334 |
+
"NNC": 382,
|
| 335 |
+
"NO": 719,
|
| 336 |
+
"NS": 377,
|
| 337 |
+
"NSC": 736,
|
| 338 |
+
"Ncc": 517,
|
| 339 |
+
"NccC": 537,
|
| 340 |
+
"Nccc": 442,
|
| 341 |
+
"NcccC": 465,
|
| 342 |
+
"NcccCl": 565,
|
| 343 |
+
"NcccF": 666,
|
| 344 |
+
"Ncccc": 303,
|
| 345 |
+
"NccccBr": 590,
|
| 346 |
+
"NccccC": 387,
|
| 347 |
+
"NccccCC": 694,
|
| 348 |
+
"NccccCl": 431,
|
| 349 |
+
"NccccF": 395,
|
| 350 |
+
"NccccNC": 528,
|
| 351 |
+
"NccccOC": 660,
|
| 352 |
+
"NccccS": 589,
|
| 353 |
+
"Nccccc": 410,
|
| 354 |
+
"NcccccC": 414,
|
| 355 |
+
"NcccccCF": 699,
|
| 356 |
+
"NcccccCl": 485,
|
| 357 |
+
"NcccccF": 639,
|
| 358 |
+
"NcccccNC": 662,
|
| 359 |
+
"Ncccccc": 323,
|
| 360 |
+
"Nccccnc": 603,
|
| 361 |
+
"Ncccnn": 718,
|
| 362 |
+
"Nccn": 723,
|
| 363 |
+
"Nccnn": 700,
|
| 364 |
+
"Ncn": 424,
|
| 365 |
+
"Ncnc": 495,
|
| 366 |
+
"NcncC": 706,
|
| 367 |
+
"Ncncc": 710,
|
| 368 |
+
"Ncncccc": 727,
|
| 369 |
+
"Ncnccs": 618,
|
| 370 |
+
"Ncncnc": 684,
|
| 371 |
+
"Ncnnc": 577,
|
| 372 |
+
"Ncsccc": 745,
|
| 373 |
+
"O": 51,
|
| 374 |
+
"OC": 287,
|
| 375 |
+
"OCC": 297,
|
| 376 |
+
"OCCC": 600,
|
| 377 |
+
"OCCCC": 629,
|
| 378 |
+
"OCCCCC": 682,
|
| 379 |
+
"OCCCO": 631,
|
| 380 |
+
"OCCF": 556,
|
| 381 |
+
"OCCO": 405,
|
| 382 |
+
"OCF": 466,
|
| 383 |
+
"OCO": 394,
|
| 384 |
+
"OCcccccc": 567,
|
| 385 |
+
"Occcc": 697,
|
| 386 |
+
"OccccC": 609,
|
| 387 |
+
"OccccCl": 695,
|
| 388 |
+
"OccccF": 738,
|
| 389 |
+
"Occcccc": 406,
|
| 390 |
+
"P": 52,
|
| 391 |
+
"Q": 53,
|
| 392 |
+
"R": 54,
|
| 393 |
+
"S": 55,
|
| 394 |
+
"SC": 333,
|
| 395 |
+
"SCC": 370,
|
| 396 |
+
"Scccccc": 583,
|
| 397 |
+
"Scnnc": 616,
|
| 398 |
+
"T": 56,
|
| 399 |
+
"U": 57,
|
| 400 |
+
"V": 58,
|
| 401 |
+
"W": 59,
|
| 402 |
+
"X": 60,
|
| 403 |
+
"Y": 61,
|
| 404 |
+
"Z": 62,
|
| 405 |
+
"[": 63,
|
| 406 |
+
"\\": 64,
|
| 407 |
+
"\\[": 649,
|
| 408 |
+
"]": 65,
|
| 409 |
+
"]%": 412,
|
| 410 |
+
"][": 320,
|
| 411 |
+
"^": 66,
|
| 412 |
+
"_": 67,
|
| 413 |
+
"`": 68,
|
| 414 |
+
"a": 69,
|
| 415 |
+
"b": 70,
|
| 416 |
+
"c": 71,
|
| 417 |
+
"cBr": 534,
|
| 418 |
+
"cC": 281,
|
| 419 |
+
"cCC": 657,
|
| 420 |
+
"cCF": 741,
|
| 421 |
+
"cCl": 327,
|
| 422 |
+
"cF": 362,
|
| 423 |
+
"cN": 549,
|
| 424 |
+
"cNC": 417,
|
| 425 |
+
"cO": 533,
|
| 426 |
+
"cOC": 409,
|
| 427 |
+
"cS": 523,
|
| 428 |
+
"cc": 262,
|
| 429 |
+
"ccBr": 550,
|
| 430 |
+
"ccC": 336,
|
| 431 |
+
"ccCl": 427,
|
| 432 |
+
"ccF": 400,
|
| 433 |
+
"ccN": 678,
|
| 434 |
+
"ccNC": 526,
|
| 435 |
+
"ccO": 677,
|
| 436 |
+
"ccOC": 511,
|
| 437 |
+
"ccc": 276,
|
| 438 |
+
"cccBr": 494,
|
| 439 |
+
"cccC": 309,
|
| 440 |
+
"cccCF": 637,
|
| 441 |
+
"cccCl": 376,
|
| 442 |
+
"cccF": 378,
|
| 443 |
+
"cccNC": 451,
|
| 444 |
+
"cccOC": 536,
|
| 445 |
+
"cccS": 574,
|
| 446 |
+
"cccc": 265,
|
| 447 |
+
"ccccBr": 390,
|
| 448 |
+
"ccccC": 284,
|
| 449 |
+
"ccccCC": 548,
|
| 450 |
+
"ccccCF": 524,
|
| 451 |
+
"ccccCNC": 515,
|
| 452 |
+
"ccccCl": 304,
|
| 453 |
+
"ccccF": 318,
|
| 454 |
+
"ccccN": 601,
|
| 455 |
+
"ccccNC": 358,
|
| 456 |
+
"ccccNCC": 713,
|
| 457 |
+
"ccccO": 435,
|
| 458 |
+
"ccccOC": 403,
|
| 459 |
+
"ccccOCC": 647,
|
| 460 |
+
"ccccOCF": 686,
|
| 461 |
+
"ccccS": 447,
|
| 462 |
+
"ccccSC": 652,
|
| 463 |
+
"ccccc": 296,
|
| 464 |
+
"cccccBr": 502,
|
| 465 |
+
"cccccC": 363,
|
| 466 |
+
"cccccCF": 541,
|
| 467 |
+
"cccccCl": 399,
|
| 468 |
+
"cccccF": 373,
|
| 469 |
+
"cccccNC": 383,
|
| 470 |
+
"cccccO": 645,
|
| 471 |
+
"cccccOC": 530,
|
| 472 |
+
"cccccS": 619,
|
| 473 |
+
"cccccc": 272,
|
| 474 |
+
"ccccccc": 632,
|
| 475 |
+
"cccccccc": 458,
|
| 476 |
+
"ccccccccc": 503,
|
| 477 |
+
"cccccccccc": 592,
|
| 478 |
+
"cccccn": 368,
|
| 479 |
+
"ccccn": 640,
|
| 480 |
+
"ccccnc": 351,
|
| 481 |
+
"cccco": 359,
|
| 482 |
+
"ccccs": 344,
|
| 483 |
+
"cccn": 463,
|
| 484 |
+
"cccnc": 497,
|
| 485 |
+
"cccncc": 379,
|
| 486 |
+
"cccnn": 664,
|
| 487 |
+
"cccoc": 540,
|
| 488 |
+
"cccsc": 422,
|
| 489 |
+
"ccn": 348,
|
| 490 |
+
"ccnC": 608,
|
| 491 |
+
"ccnc": 440,
|
| 492 |
+
"ccncC": 714,
|
| 493 |
+
"ccncc": 430,
|
| 494 |
+
"ccnccn": 595,
|
| 495 |
+
"ccnn": 404,
|
| 496 |
+
"ccnnC": 506,
|
| 497 |
+
"ccs": 468,
|
| 498 |
+
"ccsc": 444,
|
| 499 |
+
"ccscC": 712,
|
| 500 |
+
"ccscNC": 646,
|
| 501 |
+
"ccscc": 764,
|
| 502 |
+
"cn": 273,
|
| 503 |
+
"cnc": 302,
|
| 504 |
+
"cncC": 372,
|
| 505 |
+
"cncCC": 663,
|
| 506 |
+
"cncCCC": 665,
|
| 507 |
+
"cncNC": 766,
|
| 508 |
+
"cncc": 311,
|
| 509 |
+
"cnccC": 544,
|
| 510 |
+
"cnccc": 672,
|
| 511 |
+
"cncccc": 445,
|
| 512 |
+
"cncccccc": 365,
|
| 513 |
+
"cncccn": 490,
|
| 514 |
+
"cnccn": 525,
|
| 515 |
+
"cnccs": 420,
|
| 516 |
+
"cncn": 573,
|
| 517 |
+
"cncnc": 507,
|
| 518 |
+
"cncncc": 724,
|
| 519 |
+
"cncnn": 731,
|
| 520 |
+
"cnn": 322,
|
| 521 |
+
"cnnC": 470,
|
| 522 |
+
"cnnc": 340,
|
| 523 |
+
"cnncC": 504,
|
| 524 |
+
"cnncNC": 557,
|
| 525 |
+
"cnncSCC": 750,
|
| 526 |
+
"cnncccccn": 749,
|
| 527 |
+
"cnncn": 479,
|
| 528 |
+
"cnnn": 733,
|
| 529 |
+
"cnnnn": 553,
|
| 530 |
+
"cnoc": 480,
|
| 531 |
+
"cnocC": 539,
|
| 532 |
+
"co": 488,
|
| 533 |
+
"cs": 343,
|
| 534 |
+
"csc": 558,
|
| 535 |
+
"cscC": 726,
|
| 536 |
+
"csccc": 452,
|
| 537 |
+
"cscnc": 740,
|
| 538 |
+
"d": 72,
|
| 539 |
+
"e": 73,
|
| 540 |
+
"f": 74,
|
| 541 |
+
"g": 75,
|
| 542 |
+
"h": 76,
|
| 543 |
+
"i": 77,
|
| 544 |
+
"j": 78,
|
| 545 |
+
"k": 79,
|
| 546 |
+
"l": 80,
|
| 547 |
+
"m": 81,
|
| 548 |
+
"n": 82,
|
| 549 |
+
"nC": 397,
|
| 550 |
+
"nCC": 570,
|
| 551 |
+
"nH": 293,
|
| 552 |
+
"nc": 285,
|
| 553 |
+
"ncC": 388,
|
| 554 |
+
"ncN": 655,
|
| 555 |
+
"ncS": 742,
|
| 556 |
+
"ncSCC": 689,
|
| 557 |
+
"ncc": 312,
|
| 558 |
+
"nccC": 606,
|
| 559 |
+
"nccc": 702,
|
| 560 |
+
"ncccc": 521,
|
| 561 |
+
"ncccccc": 421,
|
| 562 |
+
"ncccn": 457,
|
| 563 |
+
"nccnc": 481,
|
| 564 |
+
"ncn": 396,
|
| 565 |
+
"ncnc": 527,
|
| 566 |
+
"ncncccccc": 765,
|
| 567 |
+
"ncncn": 491,
|
| 568 |
+
"ncnnc": 643,
|
| 569 |
+
"ncnnn": 638,
|
| 570 |
+
"nn": 298,
|
| 571 |
+
"nnC": 554,
|
| 572 |
+
"nnc": 380,
|
| 573 |
+
"nncC": 439,
|
| 574 |
+
"nnccc": 630,
|
| 575 |
+
"nnn": 459,
|
| 576 |
+
"nnnnc": 621,
|
| 577 |
+
"no": 364,
|
| 578 |
+
"noc": 593,
|
| 579 |
+
"o": 83,
|
| 580 |
+
"oc": 341,
|
| 581 |
+
"ocC": 413,
|
| 582 |
+
"occc": 625,
|
| 583 |
+
"occcccc": 559,
|
| 584 |
+
"on": 434,
|
| 585 |
+
"onc": 692,
|
| 586 |
+
"p": 84,
|
| 587 |
+
"q": 85,
|
| 588 |
+
"r": 86,
|
| 589 |
+
"s": 87,
|
| 590 |
+
"sc": 321,
|
| 591 |
+
"scC": 560,
|
| 592 |
+
"scNC": 760,
|
| 593 |
+
"scc": 566,
|
| 594 |
+
"sccc": 585,
|
| 595 |
+
"t": 88,
|
| 596 |
+
"u": 89,
|
| 597 |
+
"v": 90,
|
| 598 |
+
"w": 91,
|
| 599 |
+
"x": 92,
|
| 600 |
+
"y": 93,
|
| 601 |
+
"z": 94,
|
| 602 |
+
"{": 95,
|
| 603 |
+
"|": 96,
|
| 604 |
+
"}": 97,
|
| 605 |
+
"~": 98,
|
| 606 |
+
"¡": 99,
|
| 607 |
+
"¢": 100,
|
| 608 |
+
"£": 101,
|
| 609 |
+
"¤": 102,
|
| 610 |
+
"¥": 103,
|
| 611 |
+
"¦": 104,
|
| 612 |
+
"§": 105,
|
| 613 |
+
"¨": 106,
|
| 614 |
+
"©": 107,
|
| 615 |
+
"ª": 108,
|
| 616 |
+
"«": 109,
|
| 617 |
+
"¬": 110,
|
| 618 |
+
"®": 111,
|
| 619 |
+
"¯": 112,
|
| 620 |
+
"°": 113,
|
| 621 |
+
"±": 114,
|
| 622 |
+
"²": 115,
|
| 623 |
+
"³": 116,
|
| 624 |
+
"´": 117,
|
| 625 |
+
"µ": 118,
|
| 626 |
+
"¶": 119,
|
| 627 |
+
"·": 120,
|
| 628 |
+
"¸": 121,
|
| 629 |
+
"¹": 122,
|
| 630 |
+
"º": 123,
|
| 631 |
+
"»": 124,
|
| 632 |
+
"¼": 125,
|
| 633 |
+
"½": 126,
|
| 634 |
+
"¾": 127,
|
| 635 |
+
"¿": 128,
|
| 636 |
+
"À": 129,
|
| 637 |
+
"Á": 130,
|
| 638 |
+
"Â": 131,
|
| 639 |
+
"Ã": 132,
|
| 640 |
+
"Ä": 133,
|
| 641 |
+
"Å": 134,
|
| 642 |
+
"Æ": 135,
|
| 643 |
+
"Ç": 136,
|
| 644 |
+
"È": 137,
|
| 645 |
+
"É": 138,
|
| 646 |
+
"Ê": 139,
|
| 647 |
+
"Ë": 140,
|
| 648 |
+
"Ì": 141,
|
| 649 |
+
"Í": 142,
|
| 650 |
+
"Î": 143,
|
| 651 |
+
"Ï": 144,
|
| 652 |
+
"Ð": 145,
|
| 653 |
+
"Ñ": 146,
|
| 654 |
+
"Ò": 147,
|
| 655 |
+
"Ó": 148,
|
| 656 |
+
"Ô": 149,
|
| 657 |
+
"Õ": 150,
|
| 658 |
+
"Ö": 151,
|
| 659 |
+
"×": 152,
|
| 660 |
+
"Ø": 153,
|
| 661 |
+
"Ù": 154,
|
| 662 |
+
"Ú": 155,
|
| 663 |
+
"Û": 156,
|
| 664 |
+
"Ü": 157,
|
| 665 |
+
"Ý": 158,
|
| 666 |
+
"Þ": 159,
|
| 667 |
+
"ß": 160,
|
| 668 |
+
"à": 161,
|
| 669 |
+
"á": 162,
|
| 670 |
+
"â": 163,
|
| 671 |
+
"ã": 164,
|
| 672 |
+
"ä": 165,
|
| 673 |
+
"å": 166,
|
| 674 |
+
"æ": 167,
|
| 675 |
+
"ç": 168,
|
| 676 |
+
"è": 169,
|
| 677 |
+
"é": 170,
|
| 678 |
+
"ê": 171,
|
| 679 |
+
"ë": 172,
|
| 680 |
+
"ì": 173,
|
| 681 |
+
"í": 174,
|
| 682 |
+
"î": 175,
|
| 683 |
+
"ï": 176,
|
| 684 |
+
"ð": 177,
|
| 685 |
+
"ñ": 178,
|
| 686 |
+
"ò": 179,
|
| 687 |
+
"ó": 180,
|
| 688 |
+
"ô": 181,
|
| 689 |
+
"õ": 182,
|
| 690 |
+
"ö": 183,
|
| 691 |
+
"÷": 184,
|
| 692 |
+
"ø": 185,
|
| 693 |
+
"ù": 186,
|
| 694 |
+
"ú": 187,
|
| 695 |
+
"û": 188,
|
| 696 |
+
"ü": 189,
|
| 697 |
+
"ý": 190,
|
| 698 |
+
"þ": 191,
|
| 699 |
+
"ÿ": 192,
|
| 700 |
+
"Ā": 193,
|
| 701 |
+
"ā": 194,
|
| 702 |
+
"Ă": 195,
|
| 703 |
+
"ă": 196,
|
| 704 |
+
"Ą": 197,
|
| 705 |
+
"ą": 198,
|
| 706 |
+
"Ć": 199,
|
| 707 |
+
"ć": 200,
|
| 708 |
+
"Ĉ": 201,
|
| 709 |
+
"ĉ": 202,
|
| 710 |
+
"Ċ": 203,
|
| 711 |
+
"ċ": 204,
|
| 712 |
+
"Č": 205,
|
| 713 |
+
"č": 206,
|
| 714 |
+
"čĊ": 266,
|
| 715 |
+
"Ď": 207,
|
| 716 |
+
"ď": 208,
|
| 717 |
+
"Đ": 209,
|
| 718 |
+
"đ": 210,
|
| 719 |
+
"Ē": 211,
|
| 720 |
+
"ē": 212,
|
| 721 |
+
"Ĕ": 213,
|
| 722 |
+
"ĕ": 214,
|
| 723 |
+
"Ė": 215,
|
| 724 |
+
"ė": 216,
|
| 725 |
+
"Ę": 217,
|
| 726 |
+
"ę": 218,
|
| 727 |
+
"Ě": 219,
|
| 728 |
+
"ě": 220,
|
| 729 |
+
"Ĝ": 221,
|
| 730 |
+
"ĝ": 222,
|
| 731 |
+
"Ğ": 223,
|
| 732 |
+
"ğ": 224,
|
| 733 |
+
"Ġ": 225,
|
| 734 |
+
"ġ": 226,
|
| 735 |
+
"Ģ": 227,
|
| 736 |
+
"ģ": 228,
|
| 737 |
+
"Ĥ": 229,
|
| 738 |
+
"ĥ": 230,
|
| 739 |
+
"Ħ": 231,
|
| 740 |
+
"ħ": 232,
|
| 741 |
+
"Ĩ": 233,
|
| 742 |
+
"ĩ": 234,
|
| 743 |
+
"Ī": 235,
|
| 744 |
+
"ī": 236,
|
| 745 |
+
"Ĭ": 237,
|
| 746 |
+
"ĭ": 238,
|
| 747 |
+
"Į": 239,
|
| 748 |
+
"į": 240,
|
| 749 |
+
"İ": 241,
|
| 750 |
+
"ı": 242,
|
| 751 |
+
"IJ": 243,
|
| 752 |
+
"ij": 244,
|
| 753 |
+
"Ĵ": 245,
|
| 754 |
+
"ĵ": 246,
|
| 755 |
+
"Ķ": 247,
|
| 756 |
+
"ķ": 248,
|
| 757 |
+
"ĸ": 249,
|
| 758 |
+
"Ĺ": 250,
|
| 759 |
+
"ĺ": 251,
|
| 760 |
+
"Ļ": 252,
|
| 761 |
+
"ļ": 253,
|
| 762 |
+
"Ľ": 254,
|
| 763 |
+
"ľ": 255,
|
| 764 |
+
"Ŀ": 256,
|
| 765 |
+
"ŀ": 257,
|
| 766 |
+
"Ł": 258,
|
| 767 |
+
"ł": 259,
|
| 768 |
+
"Ń": 260
|
| 769 |
+
}
|