Update tokenizer_config.json
Browse files- tokenizer_config.json +53 -53
tokenizer_config.json
CHANGED
|
@@ -90,7 +90,7 @@
|
|
| 90 |
"special": true
|
| 91 |
},
|
| 92 |
"128011": {
|
| 93 |
-
"content": "<
|
| 94 |
"lstrip": false,
|
| 95 |
"normalized": false,
|
| 96 |
"rstrip": false,
|
|
@@ -98,7 +98,7 @@
|
|
| 98 |
"special": false
|
| 99 |
},
|
| 100 |
"128012": {
|
| 101 |
-
"content": "</
|
| 102 |
"lstrip": false,
|
| 103 |
"normalized": false,
|
| 104 |
"rstrip": false,
|
|
@@ -122,199 +122,199 @@
|
|
| 122 |
"special": false
|
| 123 |
},
|
| 124 |
"128015": {
|
| 125 |
-
"content": "
|
| 126 |
"lstrip": false,
|
| 127 |
"normalized": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"single_word": false,
|
| 130 |
-
"special":
|
| 131 |
},
|
| 132 |
"128016": {
|
| 133 |
-
"content": "
|
| 134 |
"lstrip": false,
|
| 135 |
"normalized": false,
|
| 136 |
"rstrip": false,
|
| 137 |
"single_word": false,
|
| 138 |
-
"special":
|
| 139 |
},
|
| 140 |
"128017": {
|
| 141 |
-
"content": "
|
| 142 |
"lstrip": false,
|
| 143 |
"normalized": false,
|
| 144 |
"rstrip": false,
|
| 145 |
"single_word": false,
|
| 146 |
-
"special":
|
| 147 |
},
|
| 148 |
"128018": {
|
| 149 |
-
"content": "
|
| 150 |
"lstrip": false,
|
| 151 |
"normalized": false,
|
| 152 |
"rstrip": false,
|
| 153 |
"single_word": false,
|
| 154 |
-
"special":
|
| 155 |
},
|
| 156 |
"128019": {
|
| 157 |
-
"content": "
|
| 158 |
"lstrip": false,
|
| 159 |
"normalized": false,
|
| 160 |
"rstrip": false,
|
| 161 |
"single_word": false,
|
| 162 |
-
"special":
|
| 163 |
},
|
| 164 |
"128020": {
|
| 165 |
-
"content": "
|
| 166 |
"lstrip": false,
|
| 167 |
"normalized": false,
|
| 168 |
"rstrip": false,
|
| 169 |
"single_word": false,
|
| 170 |
-
"special":
|
| 171 |
},
|
| 172 |
"128021": {
|
| 173 |
-
"content": "
|
| 174 |
"lstrip": false,
|
| 175 |
"normalized": false,
|
| 176 |
"rstrip": false,
|
| 177 |
"single_word": false,
|
| 178 |
-
"special":
|
| 179 |
},
|
| 180 |
"128022": {
|
| 181 |
-
"content": "
|
| 182 |
"lstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
"rstrip": false,
|
| 185 |
"single_word": false,
|
| 186 |
-
"special":
|
| 187 |
},
|
| 188 |
"128023": {
|
| 189 |
-
"content": "
|
| 190 |
"lstrip": false,
|
| 191 |
"normalized": false,
|
| 192 |
"rstrip": false,
|
| 193 |
"single_word": false,
|
| 194 |
-
"special":
|
| 195 |
},
|
| 196 |
"128024": {
|
| 197 |
-
"content": "
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": false,
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
-
"special":
|
| 203 |
},
|
| 204 |
"128025": {
|
| 205 |
-
"content": "
|
| 206 |
"lstrip": false,
|
| 207 |
"normalized": false,
|
| 208 |
"rstrip": false,
|
| 209 |
"single_word": false,
|
| 210 |
-
"special":
|
| 211 |
},
|
| 212 |
"128026": {
|
| 213 |
-
"content": "
|
| 214 |
"lstrip": false,
|
| 215 |
"normalized": false,
|
| 216 |
"rstrip": false,
|
| 217 |
"single_word": false,
|
| 218 |
-
"special":
|
| 219 |
},
|
| 220 |
"128027": {
|
| 221 |
-
"content": "
|
| 222 |
"lstrip": false,
|
| 223 |
"normalized": false,
|
| 224 |
"rstrip": false,
|
| 225 |
"single_word": false,
|
| 226 |
-
"special":
|
| 227 |
},
|
| 228 |
"128028": {
|
| 229 |
-
"content": "
|
| 230 |
"lstrip": false,
|
| 231 |
"normalized": false,
|
| 232 |
"rstrip": false,
|
| 233 |
"single_word": false,
|
| 234 |
-
"special":
|
| 235 |
},
|
| 236 |
"128029": {
|
| 237 |
-
"content": "
|
| 238 |
"lstrip": false,
|
| 239 |
"normalized": false,
|
| 240 |
"rstrip": false,
|
| 241 |
"single_word": false,
|
| 242 |
-
"special":
|
| 243 |
},
|
| 244 |
"128030": {
|
| 245 |
-
"content": "
|
| 246 |
"lstrip": false,
|
| 247 |
"normalized": false,
|
| 248 |
"rstrip": false,
|
| 249 |
"single_word": false,
|
| 250 |
-
"special":
|
| 251 |
},
|
| 252 |
"128031": {
|
| 253 |
-
"content": "
|
| 254 |
"lstrip": false,
|
| 255 |
"normalized": false,
|
| 256 |
"rstrip": false,
|
| 257 |
"single_word": false,
|
| 258 |
-
"special":
|
| 259 |
},
|
| 260 |
"128032": {
|
| 261 |
-
"content": "
|
| 262 |
"lstrip": false,
|
| 263 |
"normalized": false,
|
| 264 |
"rstrip": false,
|
| 265 |
"single_word": false,
|
| 266 |
-
"special":
|
| 267 |
},
|
| 268 |
"128033": {
|
| 269 |
-
"content": "
|
| 270 |
"lstrip": false,
|
| 271 |
"normalized": false,
|
| 272 |
"rstrip": false,
|
| 273 |
"single_word": false,
|
| 274 |
-
"special":
|
| 275 |
},
|
| 276 |
"128034": {
|
| 277 |
-
"content": "
|
| 278 |
"lstrip": false,
|
| 279 |
"normalized": false,
|
| 280 |
"rstrip": false,
|
| 281 |
"single_word": false,
|
| 282 |
-
"special":
|
| 283 |
},
|
| 284 |
"128035": {
|
| 285 |
-
"content": "
|
| 286 |
"lstrip": false,
|
| 287 |
"normalized": false,
|
| 288 |
"rstrip": false,
|
| 289 |
"single_word": false,
|
| 290 |
-
"special":
|
| 291 |
},
|
| 292 |
"128036": {
|
| 293 |
-
"content": "
|
| 294 |
"lstrip": false,
|
| 295 |
"normalized": false,
|
| 296 |
"rstrip": false,
|
| 297 |
"single_word": false,
|
| 298 |
-
"special":
|
| 299 |
},
|
| 300 |
"128037": {
|
| 301 |
-
"content": "
|
| 302 |
"lstrip": false,
|
| 303 |
"normalized": false,
|
| 304 |
"rstrip": false,
|
| 305 |
"single_word": false,
|
| 306 |
-
"special":
|
| 307 |
},
|
| 308 |
"128038": {
|
| 309 |
-
"content": "
|
| 310 |
"lstrip": false,
|
| 311 |
"normalized": false,
|
| 312 |
"rstrip": false,
|
| 313 |
"single_word": false,
|
| 314 |
-
"special":
|
| 315 |
},
|
| 316 |
"128039": {
|
| 317 |
-
"content": "<|
|
| 318 |
"lstrip": false,
|
| 319 |
"normalized": false,
|
| 320 |
"rstrip": false,
|
|
@@ -322,12 +322,12 @@
|
|
| 322 |
"special": true
|
| 323 |
},
|
| 324 |
"128040": {
|
| 325 |
-
"content": "<|
|
| 326 |
"lstrip": false,
|
| 327 |
"normalized": false,
|
| 328 |
"rstrip": false,
|
| 329 |
"single_word": false,
|
| 330 |
-
"special":
|
| 331 |
},
|
| 332 |
"128041": {
|
| 333 |
"content": "<|reserved_special_token_33|>",
|
|
|
|
| 90 |
"special": true
|
| 91 |
},
|
| 92 |
"128011": {
|
| 93 |
+
"content": "<think>",
|
| 94 |
"lstrip": false,
|
| 95 |
"normalized": false,
|
| 96 |
"rstrip": false,
|
|
|
|
| 98 |
"special": false
|
| 99 |
},
|
| 100 |
"128012": {
|
| 101 |
+
"content": "</think>",
|
| 102 |
"lstrip": false,
|
| 103 |
"normalized": false,
|
| 104 |
"rstrip": false,
|
|
|
|
| 122 |
"special": false
|
| 123 |
},
|
| 124 |
"128015": {
|
| 125 |
+
"content": "<|reserved_special_token_7|>",
|
| 126 |
"lstrip": false,
|
| 127 |
"normalized": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
},
|
| 132 |
"128016": {
|
| 133 |
+
"content": "<|reserved_special_token_8|>",
|
| 134 |
"lstrip": false,
|
| 135 |
"normalized": false,
|
| 136 |
"rstrip": false,
|
| 137 |
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
},
|
| 140 |
"128017": {
|
| 141 |
+
"content": "<|reserved_special_token_9|>",
|
| 142 |
"lstrip": false,
|
| 143 |
"normalized": false,
|
| 144 |
"rstrip": false,
|
| 145 |
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
},
|
| 148 |
"128018": {
|
| 149 |
+
"content": "<|reserved_special_token_10|>",
|
| 150 |
"lstrip": false,
|
| 151 |
"normalized": false,
|
| 152 |
"rstrip": false,
|
| 153 |
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
},
|
| 156 |
"128019": {
|
| 157 |
+
"content": "<|reserved_special_token_11|>",
|
| 158 |
"lstrip": false,
|
| 159 |
"normalized": false,
|
| 160 |
"rstrip": false,
|
| 161 |
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
},
|
| 164 |
"128020": {
|
| 165 |
+
"content": "<|reserved_special_token_12|>",
|
| 166 |
"lstrip": false,
|
| 167 |
"normalized": false,
|
| 168 |
"rstrip": false,
|
| 169 |
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
},
|
| 172 |
"128021": {
|
| 173 |
+
"content": "<|reserved_special_token_13|>",
|
| 174 |
"lstrip": false,
|
| 175 |
"normalized": false,
|
| 176 |
"rstrip": false,
|
| 177 |
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
},
|
| 180 |
"128022": {
|
| 181 |
+
"content": "<|reserved_special_token_14|>",
|
| 182 |
"lstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
"rstrip": false,
|
| 185 |
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
},
|
| 188 |
"128023": {
|
| 189 |
+
"content": "<|reserved_special_token_15|>",
|
| 190 |
"lstrip": false,
|
| 191 |
"normalized": false,
|
| 192 |
"rstrip": false,
|
| 193 |
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
},
|
| 196 |
"128024": {
|
| 197 |
+
"content": "<|reserved_special_token_16|>",
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": false,
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
},
|
| 204 |
"128025": {
|
| 205 |
+
"content": "<|reserved_special_token_17|>",
|
| 206 |
"lstrip": false,
|
| 207 |
"normalized": false,
|
| 208 |
"rstrip": false,
|
| 209 |
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
},
|
| 212 |
"128026": {
|
| 213 |
+
"content": "<|reserved_special_token_18|>",
|
| 214 |
"lstrip": false,
|
| 215 |
"normalized": false,
|
| 216 |
"rstrip": false,
|
| 217 |
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
},
|
| 220 |
"128027": {
|
| 221 |
+
"content": "<|reserved_special_token_19|>",
|
| 222 |
"lstrip": false,
|
| 223 |
"normalized": false,
|
| 224 |
"rstrip": false,
|
| 225 |
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
},
|
| 228 |
"128028": {
|
| 229 |
+
"content": "<|reserved_special_token_20|>",
|
| 230 |
"lstrip": false,
|
| 231 |
"normalized": false,
|
| 232 |
"rstrip": false,
|
| 233 |
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
},
|
| 236 |
"128029": {
|
| 237 |
+
"content": "<|reserved_special_token_21|>",
|
| 238 |
"lstrip": false,
|
| 239 |
"normalized": false,
|
| 240 |
"rstrip": false,
|
| 241 |
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
},
|
| 244 |
"128030": {
|
| 245 |
+
"content": "<|reserved_special_token_22|>",
|
| 246 |
"lstrip": false,
|
| 247 |
"normalized": false,
|
| 248 |
"rstrip": false,
|
| 249 |
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
},
|
| 252 |
"128031": {
|
| 253 |
+
"content": "<|reserved_special_token_23|>",
|
| 254 |
"lstrip": false,
|
| 255 |
"normalized": false,
|
| 256 |
"rstrip": false,
|
| 257 |
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
},
|
| 260 |
"128032": {
|
| 261 |
+
"content": "<|reserved_special_token_24|>",
|
| 262 |
"lstrip": false,
|
| 263 |
"normalized": false,
|
| 264 |
"rstrip": false,
|
| 265 |
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
},
|
| 268 |
"128033": {
|
| 269 |
+
"content": "<|reserved_special_token_25|>",
|
| 270 |
"lstrip": false,
|
| 271 |
"normalized": false,
|
| 272 |
"rstrip": false,
|
| 273 |
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
},
|
| 276 |
"128034": {
|
| 277 |
+
"content": "<|reserved_special_token_26|>",
|
| 278 |
"lstrip": false,
|
| 279 |
"normalized": false,
|
| 280 |
"rstrip": false,
|
| 281 |
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
},
|
| 284 |
"128035": {
|
| 285 |
+
"content": "<|reserved_special_token_27|>",
|
| 286 |
"lstrip": false,
|
| 287 |
"normalized": false,
|
| 288 |
"rstrip": false,
|
| 289 |
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
},
|
| 292 |
"128036": {
|
| 293 |
+
"content": "<|reserved_special_token_28|>",
|
| 294 |
"lstrip": false,
|
| 295 |
"normalized": false,
|
| 296 |
"rstrip": false,
|
| 297 |
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
},
|
| 300 |
"128037": {
|
| 301 |
+
"content": "<|reserved_special_token_29|>",
|
| 302 |
"lstrip": false,
|
| 303 |
"normalized": false,
|
| 304 |
"rstrip": false,
|
| 305 |
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
},
|
| 308 |
"128038": {
|
| 309 |
+
"content": "<|reserved_special_token_30|>",
|
| 310 |
"lstrip": false,
|
| 311 |
"normalized": false,
|
| 312 |
"rstrip": false,
|
| 313 |
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
},
|
| 316 |
"128039": {
|
| 317 |
+
"content": "<|reserved_special_token_31|>",
|
| 318 |
"lstrip": false,
|
| 319 |
"normalized": false,
|
| 320 |
"rstrip": false,
|
|
|
|
| 322 |
"special": true
|
| 323 |
},
|
| 324 |
"128040": {
|
| 325 |
+
"content": "<|reserved_special_token_32|>",
|
| 326 |
"lstrip": false,
|
| 327 |
"normalized": false,
|
| 328 |
"rstrip": false,
|
| 329 |
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
},
|
| 332 |
"128041": {
|
| 333 |
"content": "<|reserved_special_token_33|>",
|