Upload tokenizer
Browse files- tokenizer.json +64 -100
tokenizer.json
CHANGED
|
@@ -139,62 +139,62 @@
|
|
| 139 |
"<s>": 1,
|
| 140 |
"</s>": 2,
|
| 141 |
"#": 3,
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"
|
| 167 |
-
"
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"
|
| 179 |
-
"
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"(C
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"[C
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"
|
| 194 |
-
")
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
},
|
| 199 |
"merges": [
|
| 200 |
[
|
|
@@ -234,12 +234,12 @@
|
|
| 234 |
"]"
|
| 235 |
],
|
| 236 |
[
|
| 237 |
-
"
|
| 238 |
-
"
|
| 239 |
],
|
| 240 |
[
|
| 241 |
-
"[",
|
| 242 |
-
"
|
| 243 |
],
|
| 244 |
[
|
| 245 |
"c1",
|
|
@@ -249,57 +249,21 @@
|
|
| 249 |
"c",
|
| 250 |
"("
|
| 251 |
],
|
| 252 |
-
[
|
| 253 |
-
"▁",
|
| 254 |
-
"C"
|
| 255 |
-
],
|
| 256 |
-
[
|
| 257 |
-
"C",
|
| 258 |
-
"(=O)"
|
| 259 |
-
],
|
| 260 |
[
|
| 261 |
"(C",
|
| 262 |
")"
|
| 263 |
],
|
| 264 |
[
|
| 265 |
-
"
|
| 266 |
-
")"
|
| 267 |
],
|
| 268 |
[
|
| 269 |
-
"
|
| 270 |
-
"
|
| 271 |
],
|
| 272 |
[
|
| 273 |
"[C@",
|
| 274 |
"@"
|
| 275 |
-
],
|
| 276 |
-
[
|
| 277 |
-
"c",
|
| 278 |
-
"3"
|
| 279 |
-
],
|
| 280 |
-
[
|
| 281 |
-
"c2",
|
| 282 |
-
"cc"
|
| 283 |
-
],
|
| 284 |
-
[
|
| 285 |
-
"[C@@",
|
| 286 |
-
"H]"
|
| 287 |
-
],
|
| 288 |
-
[
|
| 289 |
-
")",
|
| 290 |
-
"cc"
|
| 291 |
-
],
|
| 292 |
-
[
|
| 293 |
-
"N",
|
| 294 |
-
"C(=O)"
|
| 295 |
-
],
|
| 296 |
-
[
|
| 297 |
-
"CC",
|
| 298 |
-
"C"
|
| 299 |
-
],
|
| 300 |
-
[
|
| 301 |
-
"(=O)",
|
| 302 |
-
"N"
|
| 303 |
]
|
| 304 |
]
|
| 305 |
}
|
|
|
|
| 139 |
"<s>": 1,
|
| 140 |
"</s>": 2,
|
| 141 |
"#": 3,
|
| 142 |
+
"%": 4,
|
| 143 |
+
"(": 5,
|
| 144 |
+
")": 6,
|
| 145 |
+
"+": 7,
|
| 146 |
+
"-": 8,
|
| 147 |
+
"/": 9,
|
| 148 |
+
"0": 10,
|
| 149 |
+
"1": 11,
|
| 150 |
+
"2": 12,
|
| 151 |
+
"3": 13,
|
| 152 |
+
"4": 14,
|
| 153 |
+
"5": 15,
|
| 154 |
+
"6": 16,
|
| 155 |
+
"7": 17,
|
| 156 |
+
"8": 18,
|
| 157 |
+
"9": 19,
|
| 158 |
+
"=": 20,
|
| 159 |
+
"@": 21,
|
| 160 |
+
"B": 22,
|
| 161 |
+
"C": 23,
|
| 162 |
+
"F": 24,
|
| 163 |
+
"H": 25,
|
| 164 |
+
"I": 26,
|
| 165 |
+
"N": 27,
|
| 166 |
+
"O": 28,
|
| 167 |
+
"P": 29,
|
| 168 |
+
"S": 30,
|
| 169 |
+
"[": 31,
|
| 170 |
+
"\\": 32,
|
| 171 |
+
"]": 33,
|
| 172 |
+
"c": 34,
|
| 173 |
+
"i": 35,
|
| 174 |
+
"l": 36,
|
| 175 |
+
"n": 37,
|
| 176 |
+
"o": 38,
|
| 177 |
+
"p": 39,
|
| 178 |
+
"r": 40,
|
| 179 |
+
"s": 41,
|
| 180 |
+
"▁": 42,
|
| 181 |
+
"cc": 43,
|
| 182 |
+
"CC": 44,
|
| 183 |
+
"O)": 45,
|
| 184 |
+
"c1": 46,
|
| 185 |
+
"=O)": 47,
|
| 186 |
+
"(=O)": 48,
|
| 187 |
+
"(C": 49,
|
| 188 |
+
"c2": 50,
|
| 189 |
+
"H]": 51,
|
| 190 |
+
"[C": 52,
|
| 191 |
+
"[C@": 53,
|
| 192 |
+
"c1cc": 54,
|
| 193 |
+
"c(": 55,
|
| 194 |
+
"(C)": 56,
|
| 195 |
+
"C(=O)": 57,
|
| 196 |
+
"▁C": 58,
|
| 197 |
+
"[C@@": 59
|
| 198 |
},
|
| 199 |
"merges": [
|
| 200 |
[
|
|
|
|
| 234 |
"]"
|
| 235 |
],
|
| 236 |
[
|
| 237 |
+
"[",
|
| 238 |
+
"C"
|
| 239 |
],
|
| 240 |
[
|
| 241 |
+
"[C",
|
| 242 |
+
"@"
|
| 243 |
],
|
| 244 |
[
|
| 245 |
"c1",
|
|
|
|
| 249 |
"c",
|
| 250 |
"("
|
| 251 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
[
|
| 253 |
"(C",
|
| 254 |
")"
|
| 255 |
],
|
| 256 |
[
|
| 257 |
+
"C",
|
| 258 |
+
"(=O)"
|
| 259 |
],
|
| 260 |
[
|
| 261 |
+
"▁",
|
| 262 |
+
"C"
|
| 263 |
],
|
| 264 |
[
|
| 265 |
"[C@",
|
| 266 |
"@"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 267 |
]
|
| 268 |
]
|
| 269 |
}
|