Upload 4 files
Browse files- special_tokens_map.json +135 -1
- tokenizer.json +2 -2
- tokenizer_config.json +261 -128
special_tokens_map.json
CHANGED
|
@@ -1 +1,135 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|pad|>",
|
| 4 |
+
"<|separator|>",
|
| 5 |
+
"<|eos|>",
|
| 6 |
+
"<|control1|>",
|
| 7 |
+
"<|control2|>",
|
| 8 |
+
"<|control3|>",
|
| 9 |
+
"<|control4|>",
|
| 10 |
+
"<|control5|>",
|
| 11 |
+
"<|control6|>",
|
| 12 |
+
"<|control7|>",
|
| 13 |
+
"<|control8|>",
|
| 14 |
+
"<|control9|>",
|
| 15 |
+
"<|control10|>",
|
| 16 |
+
"<|control11|>",
|
| 17 |
+
"<|control12|>",
|
| 18 |
+
"<|control13|>",
|
| 19 |
+
"<|control14|>",
|
| 20 |
+
"<|control15|>",
|
| 21 |
+
"<|control16|>",
|
| 22 |
+
"<|control17|>",
|
| 23 |
+
"<|control18|>",
|
| 24 |
+
"<|control19|>",
|
| 25 |
+
"<|control20|>",
|
| 26 |
+
"<|control21|>",
|
| 27 |
+
"<|control22|>",
|
| 28 |
+
"<|control23|>",
|
| 29 |
+
"<|control24|>",
|
| 30 |
+
"<|control25|>",
|
| 31 |
+
"<|control26|>",
|
| 32 |
+
"<|control27|>",
|
| 33 |
+
"<|control28|>",
|
| 34 |
+
"<|control29|>",
|
| 35 |
+
"<|control30|>",
|
| 36 |
+
"<|control31|>",
|
| 37 |
+
"<|control32|>",
|
| 38 |
+
"<|control33|>",
|
| 39 |
+
"<|control34|>",
|
| 40 |
+
"<|control35|>",
|
| 41 |
+
"<|control36|>",
|
| 42 |
+
"<|control37|>",
|
| 43 |
+
"<|control38|>",
|
| 44 |
+
"<|control39|>",
|
| 45 |
+
"<|control40|>",
|
| 46 |
+
"<|control41|>",
|
| 47 |
+
"<|control42|>",
|
| 48 |
+
"<|control43|>",
|
| 49 |
+
"<|control44|>",
|
| 50 |
+
"<|control45|>",
|
| 51 |
+
"<|control46|>",
|
| 52 |
+
"<|control47|>",
|
| 53 |
+
"<|control48|>",
|
| 54 |
+
"<|control49|>",
|
| 55 |
+
"<|control50|>",
|
| 56 |
+
"<|control51|>",
|
| 57 |
+
"<|control52|>",
|
| 58 |
+
"<|control53|>",
|
| 59 |
+
"<|control54|>",
|
| 60 |
+
"<|control55|>",
|
| 61 |
+
"<|control56|>",
|
| 62 |
+
"<|control57|>",
|
| 63 |
+
"<|control58|>",
|
| 64 |
+
"<|control59|>",
|
| 65 |
+
"<|control60|>",
|
| 66 |
+
"<|control61|>",
|
| 67 |
+
"<|control62|>",
|
| 68 |
+
"<|control63|>",
|
| 69 |
+
"<|control64|>",
|
| 70 |
+
"<|control65|>",
|
| 71 |
+
"<|control66|>",
|
| 72 |
+
"<|control67|>",
|
| 73 |
+
"<|control68|>",
|
| 74 |
+
"<|control69|>",
|
| 75 |
+
"<|control70|>",
|
| 76 |
+
"<|control71|>",
|
| 77 |
+
"<|control72|>",
|
| 78 |
+
"<|control73|>",
|
| 79 |
+
"<|control74|>",
|
| 80 |
+
"<|control75|>",
|
| 81 |
+
"<|control76|>",
|
| 82 |
+
"<|control77|>",
|
| 83 |
+
"<|control78|>",
|
| 84 |
+
"<|control79|>",
|
| 85 |
+
"<|control80|>",
|
| 86 |
+
"<|control81|>",
|
| 87 |
+
"<|control82|>",
|
| 88 |
+
"<|control83|>",
|
| 89 |
+
"<|control84|>",
|
| 90 |
+
"<|control85|>",
|
| 91 |
+
"<|control86|>",
|
| 92 |
+
"<|control87|>",
|
| 93 |
+
"<|control88|>",
|
| 94 |
+
"<|control89|>",
|
| 95 |
+
"<|control90|>",
|
| 96 |
+
"<|control91|>",
|
| 97 |
+
"<|control92|>",
|
| 98 |
+
"<|control93|>",
|
| 99 |
+
"<|control94|>",
|
| 100 |
+
"<|control95|>",
|
| 101 |
+
"<|control96|>",
|
| 102 |
+
"<|control97|>",
|
| 103 |
+
"<|control98|>",
|
| 104 |
+
"<|control99|>",
|
| 105 |
+
"<|control100|>",
|
| 106 |
+
"<|control101|>",
|
| 107 |
+
"<|control102|>",
|
| 108 |
+
"<|control103|>",
|
| 109 |
+
"<|control104|>",
|
| 110 |
+
"<|control105|>",
|
| 111 |
+
"<|control106|>",
|
| 112 |
+
"<|control107|>",
|
| 113 |
+
"<|control108|>",
|
| 114 |
+
"<|control109|>",
|
| 115 |
+
"<|control110|>",
|
| 116 |
+
"<|control111|>",
|
| 117 |
+
"<|control112|>",
|
| 118 |
+
"<|control113|>",
|
| 119 |
+
"<|control114|>",
|
| 120 |
+
"<|control115|>",
|
| 121 |
+
"<|control116|>",
|
| 122 |
+
"<|control117|>",
|
| 123 |
+
"<|control118|>",
|
| 124 |
+
"<|control119|>",
|
| 125 |
+
"<|control120|>",
|
| 126 |
+
"<|control121|>",
|
| 127 |
+
"<|control122|>",
|
| 128 |
+
"<|control123|>",
|
| 129 |
+
"<|control124|>",
|
| 130 |
+
"<|control125|>"
|
| 131 |
+
],
|
| 132 |
+
"eos_token": "<|eos|>",
|
| 133 |
+
"pad_token": "<|pad|>",
|
| 134 |
+
"sep_token": "<|separator|>"
|
| 135 |
+
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e538a53de71acf0585603a7f1f62cc66c5e6fa5763d753d10ad071f5c5d4fe
|
| 3 |
+
size 17963143
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"
|
| 4 |
"content": "<|pad|>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
"content": "<|separator|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"content": "<|eos|>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
"content": "<|control1|>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
"content": "<|control2|>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
@@ -40,7 +40,7 @@
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
"content": "<|control3|>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
|
@@ -48,7 +48,7 @@
|
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
-
"
|
| 52 |
"content": "<|control4|>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
@@ -56,7 +56,7 @@
|
|
| 56 |
"single_word": false,
|
| 57 |
"special": true
|
| 58 |
},
|
| 59 |
-
"
|
| 60 |
"content": "<|control5|>",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": false,
|
|
@@ -64,7 +64,7 @@
|
|
| 64 |
"single_word": false,
|
| 65 |
"special": true
|
| 66 |
},
|
| 67 |
-
"
|
| 68 |
"content": "<|control6|>",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": false,
|
|
@@ -72,7 +72,7 @@
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
-
"
|
| 76 |
"content": "<|control7|>",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
|
@@ -80,7 +80,7 @@
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": true
|
| 82 |
},
|
| 83 |
-
"
|
| 84 |
"content": "<|control8|>",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": false,
|
|
@@ -88,7 +88,7 @@
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": true
|
| 90 |
},
|
| 91 |
-
"
|
| 92 |
"content": "<|control9|>",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": false,
|
|
@@ -96,7 +96,7 @@
|
|
| 96 |
"single_word": false,
|
| 97 |
"special": true
|
| 98 |
},
|
| 99 |
-
"
|
| 100 |
"content": "<|control10|>",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": false,
|
|
@@ -104,7 +104,7 @@
|
|
| 104 |
"single_word": false,
|
| 105 |
"special": true
|
| 106 |
},
|
| 107 |
-
"
|
| 108 |
"content": "<|control11|>",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": false,
|
|
@@ -112,7 +112,7 @@
|
|
| 112 |
"single_word": false,
|
| 113 |
"special": true
|
| 114 |
},
|
| 115 |
-
"
|
| 116 |
"content": "<|control12|>",
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": false,
|
|
@@ -120,7 +120,7 @@
|
|
| 120 |
"single_word": false,
|
| 121 |
"special": true
|
| 122 |
},
|
| 123 |
-
"
|
| 124 |
"content": "<|control13|>",
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": false,
|
|
@@ -128,7 +128,7 @@
|
|
| 128 |
"single_word": false,
|
| 129 |
"special": true
|
| 130 |
},
|
| 131 |
-
"
|
| 132 |
"content": "<|control14|>",
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": false,
|
|
@@ -136,7 +136,7 @@
|
|
| 136 |
"single_word": false,
|
| 137 |
"special": true
|
| 138 |
},
|
| 139 |
-
"
|
| 140 |
"content": "<|control15|>",
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": false,
|
|
@@ -144,7 +144,7 @@
|
|
| 144 |
"single_word": false,
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
-
"
|
| 148 |
"content": "<|control16|>",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
|
@@ -152,7 +152,7 @@
|
|
| 152 |
"single_word": false,
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
-
"
|
| 156 |
"content": "<|control17|>",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
|
@@ -160,7 +160,7 @@
|
|
| 160 |
"single_word": false,
|
| 161 |
"special": true
|
| 162 |
},
|
| 163 |
-
"
|
| 164 |
"content": "<|control18|>",
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": false,
|
|
@@ -168,7 +168,7 @@
|
|
| 168 |
"single_word": false,
|
| 169 |
"special": true
|
| 170 |
},
|
| 171 |
-
"
|
| 172 |
"content": "<|control19|>",
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": false,
|
|
@@ -176,7 +176,7 @@
|
|
| 176 |
"single_word": false,
|
| 177 |
"special": true
|
| 178 |
},
|
| 179 |
-
"
|
| 180 |
"content": "<|control20|>",
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": false,
|
|
@@ -184,7 +184,7 @@
|
|
| 184 |
"single_word": false,
|
| 185 |
"special": true
|
| 186 |
},
|
| 187 |
-
"
|
| 188 |
"content": "<|control21|>",
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": false,
|
|
@@ -192,7 +192,7 @@
|
|
| 192 |
"single_word": false,
|
| 193 |
"special": true
|
| 194 |
},
|
| 195 |
-
"
|
| 196 |
"content": "<|control22|>",
|
| 197 |
"lstrip": false,
|
| 198 |
"normalized": false,
|
|
@@ -200,7 +200,7 @@
|
|
| 200 |
"single_word": false,
|
| 201 |
"special": true
|
| 202 |
},
|
| 203 |
-
"
|
| 204 |
"content": "<|control23|>",
|
| 205 |
"lstrip": false,
|
| 206 |
"normalized": false,
|
|
@@ -208,7 +208,7 @@
|
|
| 208 |
"single_word": false,
|
| 209 |
"special": true
|
| 210 |
},
|
| 211 |
-
"
|
| 212 |
"content": "<|control24|>",
|
| 213 |
"lstrip": false,
|
| 214 |
"normalized": false,
|
|
@@ -216,7 +216,7 @@
|
|
| 216 |
"single_word": false,
|
| 217 |
"special": true
|
| 218 |
},
|
| 219 |
-
"
|
| 220 |
"content": "<|control25|>",
|
| 221 |
"lstrip": false,
|
| 222 |
"normalized": false,
|
|
@@ -224,7 +224,7 @@
|
|
| 224 |
"single_word": false,
|
| 225 |
"special": true
|
| 226 |
},
|
| 227 |
-
"
|
| 228 |
"content": "<|control26|>",
|
| 229 |
"lstrip": false,
|
| 230 |
"normalized": false,
|
|
@@ -232,7 +232,7 @@
|
|
| 232 |
"single_word": false,
|
| 233 |
"special": true
|
| 234 |
},
|
| 235 |
-
"
|
| 236 |
"content": "<|control27|>",
|
| 237 |
"lstrip": false,
|
| 238 |
"normalized": false,
|
|
@@ -240,7 +240,7 @@
|
|
| 240 |
"single_word": false,
|
| 241 |
"special": true
|
| 242 |
},
|
| 243 |
-
"
|
| 244 |
"content": "<|control28|>",
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": false,
|
|
@@ -248,7 +248,7 @@
|
|
| 248 |
"single_word": false,
|
| 249 |
"special": true
|
| 250 |
},
|
| 251 |
-
"
|
| 252 |
"content": "<|control29|>",
|
| 253 |
"lstrip": false,
|
| 254 |
"normalized": false,
|
|
@@ -256,7 +256,7 @@
|
|
| 256 |
"single_word": false,
|
| 257 |
"special": true
|
| 258 |
},
|
| 259 |
-
"
|
| 260 |
"content": "<|control30|>",
|
| 261 |
"lstrip": false,
|
| 262 |
"normalized": false,
|
|
@@ -264,7 +264,7 @@
|
|
| 264 |
"single_word": false,
|
| 265 |
"special": true
|
| 266 |
},
|
| 267 |
-
"
|
| 268 |
"content": "<|control31|>",
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": false,
|
|
@@ -272,7 +272,7 @@
|
|
| 272 |
"single_word": false,
|
| 273 |
"special": true
|
| 274 |
},
|
| 275 |
-
"
|
| 276 |
"content": "<|control32|>",
|
| 277 |
"lstrip": false,
|
| 278 |
"normalized": false,
|
|
@@ -280,7 +280,7 @@
|
|
| 280 |
"single_word": false,
|
| 281 |
"special": true
|
| 282 |
},
|
| 283 |
-
"
|
| 284 |
"content": "<|control33|>",
|
| 285 |
"lstrip": false,
|
| 286 |
"normalized": false,
|
|
@@ -288,7 +288,7 @@
|
|
| 288 |
"single_word": false,
|
| 289 |
"special": true
|
| 290 |
},
|
| 291 |
-
"
|
| 292 |
"content": "<|control34|>",
|
| 293 |
"lstrip": false,
|
| 294 |
"normalized": false,
|
|
@@ -296,7 +296,7 @@
|
|
| 296 |
"single_word": false,
|
| 297 |
"special": true
|
| 298 |
},
|
| 299 |
-
"
|
| 300 |
"content": "<|control35|>",
|
| 301 |
"lstrip": false,
|
| 302 |
"normalized": false,
|
|
@@ -304,7 +304,7 @@
|
|
| 304 |
"single_word": false,
|
| 305 |
"special": true
|
| 306 |
},
|
| 307 |
-
"
|
| 308 |
"content": "<|control36|>",
|
| 309 |
"lstrip": false,
|
| 310 |
"normalized": false,
|
|
@@ -312,7 +312,7 @@
|
|
| 312 |
"single_word": false,
|
| 313 |
"special": true
|
| 314 |
},
|
| 315 |
-
"
|
| 316 |
"content": "<|control37|>",
|
| 317 |
"lstrip": false,
|
| 318 |
"normalized": false,
|
|
@@ -320,7 +320,7 @@
|
|
| 320 |
"single_word": false,
|
| 321 |
"special": true
|
| 322 |
},
|
| 323 |
-
"
|
| 324 |
"content": "<|control38|>",
|
| 325 |
"lstrip": false,
|
| 326 |
"normalized": false,
|
|
@@ -328,7 +328,7 @@
|
|
| 328 |
"single_word": false,
|
| 329 |
"special": true
|
| 330 |
},
|
| 331 |
-
"
|
| 332 |
"content": "<|control39|>",
|
| 333 |
"lstrip": false,
|
| 334 |
"normalized": false,
|
|
@@ -336,7 +336,7 @@
|
|
| 336 |
"single_word": false,
|
| 337 |
"special": true
|
| 338 |
},
|
| 339 |
-
"
|
| 340 |
"content": "<|control40|>",
|
| 341 |
"lstrip": false,
|
| 342 |
"normalized": false,
|
|
@@ -344,7 +344,7 @@
|
|
| 344 |
"single_word": false,
|
| 345 |
"special": true
|
| 346 |
},
|
| 347 |
-
"
|
| 348 |
"content": "<|control41|>",
|
| 349 |
"lstrip": false,
|
| 350 |
"normalized": false,
|
|
@@ -352,7 +352,7 @@
|
|
| 352 |
"single_word": false,
|
| 353 |
"special": true
|
| 354 |
},
|
| 355 |
-
"
|
| 356 |
"content": "<|control42|>",
|
| 357 |
"lstrip": false,
|
| 358 |
"normalized": false,
|
|
@@ -360,7 +360,7 @@
|
|
| 360 |
"single_word": false,
|
| 361 |
"special": true
|
| 362 |
},
|
| 363 |
-
"
|
| 364 |
"content": "<|control43|>",
|
| 365 |
"lstrip": false,
|
| 366 |
"normalized": false,
|
|
@@ -368,7 +368,7 @@
|
|
| 368 |
"single_word": false,
|
| 369 |
"special": true
|
| 370 |
},
|
| 371 |
-
"
|
| 372 |
"content": "<|control44|>",
|
| 373 |
"lstrip": false,
|
| 374 |
"normalized": false,
|
|
@@ -376,7 +376,7 @@
|
|
| 376 |
"single_word": false,
|
| 377 |
"special": true
|
| 378 |
},
|
| 379 |
-
"
|
| 380 |
"content": "<|control45|>",
|
| 381 |
"lstrip": false,
|
| 382 |
"normalized": false,
|
|
@@ -384,7 +384,7 @@
|
|
| 384 |
"single_word": false,
|
| 385 |
"special": true
|
| 386 |
},
|
| 387 |
-
"
|
| 388 |
"content": "<|control46|>",
|
| 389 |
"lstrip": false,
|
| 390 |
"normalized": false,
|
|
@@ -392,7 +392,7 @@
|
|
| 392 |
"single_word": false,
|
| 393 |
"special": true
|
| 394 |
},
|
| 395 |
-
"
|
| 396 |
"content": "<|control47|>",
|
| 397 |
"lstrip": false,
|
| 398 |
"normalized": false,
|
|
@@ -400,7 +400,7 @@
|
|
| 400 |
"single_word": false,
|
| 401 |
"special": true
|
| 402 |
},
|
| 403 |
-
"
|
| 404 |
"content": "<|control48|>",
|
| 405 |
"lstrip": false,
|
| 406 |
"normalized": false,
|
|
@@ -408,7 +408,7 @@
|
|
| 408 |
"single_word": false,
|
| 409 |
"special": true
|
| 410 |
},
|
| 411 |
-
"
|
| 412 |
"content": "<|control49|>",
|
| 413 |
"lstrip": false,
|
| 414 |
"normalized": false,
|
|
@@ -416,7 +416,7 @@
|
|
| 416 |
"single_word": false,
|
| 417 |
"special": true
|
| 418 |
},
|
| 419 |
-
"
|
| 420 |
"content": "<|control50|>",
|
| 421 |
"lstrip": false,
|
| 422 |
"normalized": false,
|
|
@@ -424,7 +424,7 @@
|
|
| 424 |
"single_word": false,
|
| 425 |
"special": true
|
| 426 |
},
|
| 427 |
-
"
|
| 428 |
"content": "<|control51|>",
|
| 429 |
"lstrip": false,
|
| 430 |
"normalized": false,
|
|
@@ -432,7 +432,7 @@
|
|
| 432 |
"single_word": false,
|
| 433 |
"special": true
|
| 434 |
},
|
| 435 |
-
"
|
| 436 |
"content": "<|control52|>",
|
| 437 |
"lstrip": false,
|
| 438 |
"normalized": false,
|
|
@@ -440,7 +440,7 @@
|
|
| 440 |
"single_word": false,
|
| 441 |
"special": true
|
| 442 |
},
|
| 443 |
-
"
|
| 444 |
"content": "<|control53|>",
|
| 445 |
"lstrip": false,
|
| 446 |
"normalized": false,
|
|
@@ -448,7 +448,7 @@
|
|
| 448 |
"single_word": false,
|
| 449 |
"special": true
|
| 450 |
},
|
| 451 |
-
"
|
| 452 |
"content": "<|control54|>",
|
| 453 |
"lstrip": false,
|
| 454 |
"normalized": false,
|
|
@@ -456,7 +456,7 @@
|
|
| 456 |
"single_word": false,
|
| 457 |
"special": true
|
| 458 |
},
|
| 459 |
-
"
|
| 460 |
"content": "<|control55|>",
|
| 461 |
"lstrip": false,
|
| 462 |
"normalized": false,
|
|
@@ -464,7 +464,7 @@
|
|
| 464 |
"single_word": false,
|
| 465 |
"special": true
|
| 466 |
},
|
| 467 |
-
"
|
| 468 |
"content": "<|control56|>",
|
| 469 |
"lstrip": false,
|
| 470 |
"normalized": false,
|
|
@@ -472,7 +472,7 @@
|
|
| 472 |
"single_word": false,
|
| 473 |
"special": true
|
| 474 |
},
|
| 475 |
-
"
|
| 476 |
"content": "<|control57|>",
|
| 477 |
"lstrip": false,
|
| 478 |
"normalized": false,
|
|
@@ -480,7 +480,7 @@
|
|
| 480 |
"single_word": false,
|
| 481 |
"special": true
|
| 482 |
},
|
| 483 |
-
"
|
| 484 |
"content": "<|control58|>",
|
| 485 |
"lstrip": false,
|
| 486 |
"normalized": false,
|
|
@@ -488,7 +488,7 @@
|
|
| 488 |
"single_word": false,
|
| 489 |
"special": true
|
| 490 |
},
|
| 491 |
-
"
|
| 492 |
"content": "<|control59|>",
|
| 493 |
"lstrip": false,
|
| 494 |
"normalized": false,
|
|
@@ -496,7 +496,7 @@
|
|
| 496 |
"single_word": false,
|
| 497 |
"special": true
|
| 498 |
},
|
| 499 |
-
"
|
| 500 |
"content": "<|control60|>",
|
| 501 |
"lstrip": false,
|
| 502 |
"normalized": false,
|
|
@@ -504,7 +504,7 @@
|
|
| 504 |
"single_word": false,
|
| 505 |
"special": true
|
| 506 |
},
|
| 507 |
-
"
|
| 508 |
"content": "<|control61|>",
|
| 509 |
"lstrip": false,
|
| 510 |
"normalized": false,
|
|
@@ -512,7 +512,7 @@
|
|
| 512 |
"single_word": false,
|
| 513 |
"special": true
|
| 514 |
},
|
| 515 |
-
"
|
| 516 |
"content": "<|control62|>",
|
| 517 |
"lstrip": false,
|
| 518 |
"normalized": false,
|
|
@@ -520,7 +520,7 @@
|
|
| 520 |
"single_word": false,
|
| 521 |
"special": true
|
| 522 |
},
|
| 523 |
-
"
|
| 524 |
"content": "<|control63|>",
|
| 525 |
"lstrip": false,
|
| 526 |
"normalized": false,
|
|
@@ -528,7 +528,7 @@
|
|
| 528 |
"single_word": false,
|
| 529 |
"special": true
|
| 530 |
},
|
| 531 |
-
"
|
| 532 |
"content": "<|control64|>",
|
| 533 |
"lstrip": false,
|
| 534 |
"normalized": false,
|
|
@@ -536,7 +536,7 @@
|
|
| 536 |
"single_word": false,
|
| 537 |
"special": true
|
| 538 |
},
|
| 539 |
-
"
|
| 540 |
"content": "<|control65|>",
|
| 541 |
"lstrip": false,
|
| 542 |
"normalized": false,
|
|
@@ -544,7 +544,7 @@
|
|
| 544 |
"single_word": false,
|
| 545 |
"special": true
|
| 546 |
},
|
| 547 |
-
"
|
| 548 |
"content": "<|control66|>",
|
| 549 |
"lstrip": false,
|
| 550 |
"normalized": false,
|
|
@@ -552,7 +552,7 @@
|
|
| 552 |
"single_word": false,
|
| 553 |
"special": true
|
| 554 |
},
|
| 555 |
-
"
|
| 556 |
"content": "<|control67|>",
|
| 557 |
"lstrip": false,
|
| 558 |
"normalized": false,
|
|
@@ -560,7 +560,7 @@
|
|
| 560 |
"single_word": false,
|
| 561 |
"special": true
|
| 562 |
},
|
| 563 |
-
"
|
| 564 |
"content": "<|control68|>",
|
| 565 |
"lstrip": false,
|
| 566 |
"normalized": false,
|
|
@@ -568,7 +568,7 @@
|
|
| 568 |
"single_word": false,
|
| 569 |
"special": true
|
| 570 |
},
|
| 571 |
-
"
|
| 572 |
"content": "<|control69|>",
|
| 573 |
"lstrip": false,
|
| 574 |
"normalized": false,
|
|
@@ -576,7 +576,7 @@
|
|
| 576 |
"single_word": false,
|
| 577 |
"special": true
|
| 578 |
},
|
| 579 |
-
"
|
| 580 |
"content": "<|control70|>",
|
| 581 |
"lstrip": false,
|
| 582 |
"normalized": false,
|
|
@@ -584,7 +584,7 @@
|
|
| 584 |
"single_word": false,
|
| 585 |
"special": true
|
| 586 |
},
|
| 587 |
-
"
|
| 588 |
"content": "<|control71|>",
|
| 589 |
"lstrip": false,
|
| 590 |
"normalized": false,
|
|
@@ -592,7 +592,7 @@
|
|
| 592 |
"single_word": false,
|
| 593 |
"special": true
|
| 594 |
},
|
| 595 |
-
"
|
| 596 |
"content": "<|control72|>",
|
| 597 |
"lstrip": false,
|
| 598 |
"normalized": false,
|
|
@@ -600,7 +600,7 @@
|
|
| 600 |
"single_word": false,
|
| 601 |
"special": true
|
| 602 |
},
|
| 603 |
-
"
|
| 604 |
"content": "<|control73|>",
|
| 605 |
"lstrip": false,
|
| 606 |
"normalized": false,
|
|
@@ -608,7 +608,7 @@
|
|
| 608 |
"single_word": false,
|
| 609 |
"special": true
|
| 610 |
},
|
| 611 |
-
"
|
| 612 |
"content": "<|control74|>",
|
| 613 |
"lstrip": false,
|
| 614 |
"normalized": false,
|
|
@@ -616,7 +616,7 @@
|
|
| 616 |
"single_word": false,
|
| 617 |
"special": true
|
| 618 |
},
|
| 619 |
-
"
|
| 620 |
"content": "<|control75|>",
|
| 621 |
"lstrip": false,
|
| 622 |
"normalized": false,
|
|
@@ -624,7 +624,7 @@
|
|
| 624 |
"single_word": false,
|
| 625 |
"special": true
|
| 626 |
},
|
| 627 |
-
"
|
| 628 |
"content": "<|control76|>",
|
| 629 |
"lstrip": false,
|
| 630 |
"normalized": false,
|
|
@@ -632,7 +632,7 @@
|
|
| 632 |
"single_word": false,
|
| 633 |
"special": true
|
| 634 |
},
|
| 635 |
-
"
|
| 636 |
"content": "<|control77|>",
|
| 637 |
"lstrip": false,
|
| 638 |
"normalized": false,
|
|
@@ -640,7 +640,7 @@
|
|
| 640 |
"single_word": false,
|
| 641 |
"special": true
|
| 642 |
},
|
| 643 |
-
"
|
| 644 |
"content": "<|control78|>",
|
| 645 |
"lstrip": false,
|
| 646 |
"normalized": false,
|
|
@@ -648,7 +648,7 @@
|
|
| 648 |
"single_word": false,
|
| 649 |
"special": true
|
| 650 |
},
|
| 651 |
-
"
|
| 652 |
"content": "<|control79|>",
|
| 653 |
"lstrip": false,
|
| 654 |
"normalized": false,
|
|
@@ -656,7 +656,7 @@
|
|
| 656 |
"single_word": false,
|
| 657 |
"special": true
|
| 658 |
},
|
| 659 |
-
"
|
| 660 |
"content": "<|control80|>",
|
| 661 |
"lstrip": false,
|
| 662 |
"normalized": false,
|
|
@@ -664,7 +664,7 @@
|
|
| 664 |
"single_word": false,
|
| 665 |
"special": true
|
| 666 |
},
|
| 667 |
-
"
|
| 668 |
"content": "<|control81|>",
|
| 669 |
"lstrip": false,
|
| 670 |
"normalized": false,
|
|
@@ -672,7 +672,7 @@
|
|
| 672 |
"single_word": false,
|
| 673 |
"special": true
|
| 674 |
},
|
| 675 |
-
"
|
| 676 |
"content": "<|control82|>",
|
| 677 |
"lstrip": false,
|
| 678 |
"normalized": false,
|
|
@@ -680,7 +680,7 @@
|
|
| 680 |
"single_word": false,
|
| 681 |
"special": true
|
| 682 |
},
|
| 683 |
-
"
|
| 684 |
"content": "<|control83|>",
|
| 685 |
"lstrip": false,
|
| 686 |
"normalized": false,
|
|
@@ -688,7 +688,7 @@
|
|
| 688 |
"single_word": false,
|
| 689 |
"special": true
|
| 690 |
},
|
| 691 |
-
"
|
| 692 |
"content": "<|control84|>",
|
| 693 |
"lstrip": false,
|
| 694 |
"normalized": false,
|
|
@@ -696,7 +696,7 @@
|
|
| 696 |
"single_word": false,
|
| 697 |
"special": true
|
| 698 |
},
|
| 699 |
-
"
|
| 700 |
"content": "<|control85|>",
|
| 701 |
"lstrip": false,
|
| 702 |
"normalized": false,
|
|
@@ -704,7 +704,7 @@
|
|
| 704 |
"single_word": false,
|
| 705 |
"special": true
|
| 706 |
},
|
| 707 |
-
"
|
| 708 |
"content": "<|control86|>",
|
| 709 |
"lstrip": false,
|
| 710 |
"normalized": false,
|
|
@@ -712,7 +712,7 @@
|
|
| 712 |
"single_word": false,
|
| 713 |
"special": true
|
| 714 |
},
|
| 715 |
-
"
|
| 716 |
"content": "<|control87|>",
|
| 717 |
"lstrip": false,
|
| 718 |
"normalized": false,
|
|
@@ -720,7 +720,7 @@
|
|
| 720 |
"single_word": false,
|
| 721 |
"special": true
|
| 722 |
},
|
| 723 |
-
"
|
| 724 |
"content": "<|control88|>",
|
| 725 |
"lstrip": false,
|
| 726 |
"normalized": false,
|
|
@@ -728,7 +728,7 @@
|
|
| 728 |
"single_word": false,
|
| 729 |
"special": true
|
| 730 |
},
|
| 731 |
-
"
|
| 732 |
"content": "<|control89|>",
|
| 733 |
"lstrip": false,
|
| 734 |
"normalized": false,
|
|
@@ -736,7 +736,7 @@
|
|
| 736 |
"single_word": false,
|
| 737 |
"special": true
|
| 738 |
},
|
| 739 |
-
"
|
| 740 |
"content": "<|control90|>",
|
| 741 |
"lstrip": false,
|
| 742 |
"normalized": false,
|
|
@@ -744,7 +744,7 @@
|
|
| 744 |
"single_word": false,
|
| 745 |
"special": true
|
| 746 |
},
|
| 747 |
-
"
|
| 748 |
"content": "<|control91|>",
|
| 749 |
"lstrip": false,
|
| 750 |
"normalized": false,
|
|
@@ -752,7 +752,7 @@
|
|
| 752 |
"single_word": false,
|
| 753 |
"special": true
|
| 754 |
},
|
| 755 |
-
"
|
| 756 |
"content": "<|control92|>",
|
| 757 |
"lstrip": false,
|
| 758 |
"normalized": false,
|
|
@@ -760,7 +760,7 @@
|
|
| 760 |
"single_word": false,
|
| 761 |
"special": true
|
| 762 |
},
|
| 763 |
-
"
|
| 764 |
"content": "<|control93|>",
|
| 765 |
"lstrip": false,
|
| 766 |
"normalized": false,
|
|
@@ -768,7 +768,7 @@
|
|
| 768 |
"single_word": false,
|
| 769 |
"special": true
|
| 770 |
},
|
| 771 |
-
"
|
| 772 |
"content": "<|control94|>",
|
| 773 |
"lstrip": false,
|
| 774 |
"normalized": false,
|
|
@@ -776,7 +776,7 @@
|
|
| 776 |
"single_word": false,
|
| 777 |
"special": true
|
| 778 |
},
|
| 779 |
-
"
|
| 780 |
"content": "<|control95|>",
|
| 781 |
"lstrip": false,
|
| 782 |
"normalized": false,
|
|
@@ -784,7 +784,7 @@
|
|
| 784 |
"single_word": false,
|
| 785 |
"special": true
|
| 786 |
},
|
| 787 |
-
"
|
| 788 |
"content": "<|control96|>",
|
| 789 |
"lstrip": false,
|
| 790 |
"normalized": false,
|
|
@@ -792,7 +792,7 @@
|
|
| 792 |
"single_word": false,
|
| 793 |
"special": true
|
| 794 |
},
|
| 795 |
-
"
|
| 796 |
"content": "<|control97|>",
|
| 797 |
"lstrip": false,
|
| 798 |
"normalized": false,
|
|
@@ -800,7 +800,7 @@
|
|
| 800 |
"single_word": false,
|
| 801 |
"special": true
|
| 802 |
},
|
| 803 |
-
"
|
| 804 |
"content": "<|control98|>",
|
| 805 |
"lstrip": false,
|
| 806 |
"normalized": false,
|
|
@@ -808,7 +808,7 @@
|
|
| 808 |
"single_word": false,
|
| 809 |
"special": true
|
| 810 |
},
|
| 811 |
-
"
|
| 812 |
"content": "<|control99|>",
|
| 813 |
"lstrip": false,
|
| 814 |
"normalized": false,
|
|
@@ -816,7 +816,7 @@
|
|
| 816 |
"single_word": false,
|
| 817 |
"special": true
|
| 818 |
},
|
| 819 |
-
"
|
| 820 |
"content": "<|control100|>",
|
| 821 |
"lstrip": false,
|
| 822 |
"normalized": false,
|
|
@@ -824,7 +824,7 @@
|
|
| 824 |
"single_word": false,
|
| 825 |
"special": true
|
| 826 |
},
|
| 827 |
-
"
|
| 828 |
"content": "<|control101|>",
|
| 829 |
"lstrip": false,
|
| 830 |
"normalized": false,
|
|
@@ -832,7 +832,7 @@
|
|
| 832 |
"single_word": false,
|
| 833 |
"special": true
|
| 834 |
},
|
| 835 |
-
"
|
| 836 |
"content": "<|control102|>",
|
| 837 |
"lstrip": false,
|
| 838 |
"normalized": false,
|
|
@@ -840,7 +840,7 @@
|
|
| 840 |
"single_word": false,
|
| 841 |
"special": true
|
| 842 |
},
|
| 843 |
-
"
|
| 844 |
"content": "<|control103|>",
|
| 845 |
"lstrip": false,
|
| 846 |
"normalized": false,
|
|
@@ -848,7 +848,7 @@
|
|
| 848 |
"single_word": false,
|
| 849 |
"special": true
|
| 850 |
},
|
| 851 |
-
"
|
| 852 |
"content": "<|control104|>",
|
| 853 |
"lstrip": false,
|
| 854 |
"normalized": false,
|
|
@@ -856,7 +856,7 @@
|
|
| 856 |
"single_word": false,
|
| 857 |
"special": true
|
| 858 |
},
|
| 859 |
-
"
|
| 860 |
"content": "<|control105|>",
|
| 861 |
"lstrip": false,
|
| 862 |
"normalized": false,
|
|
@@ -864,7 +864,7 @@
|
|
| 864 |
"single_word": false,
|
| 865 |
"special": true
|
| 866 |
},
|
| 867 |
-
"
|
| 868 |
"content": "<|control106|>",
|
| 869 |
"lstrip": false,
|
| 870 |
"normalized": false,
|
|
@@ -872,7 +872,7 @@
|
|
| 872 |
"single_word": false,
|
| 873 |
"special": true
|
| 874 |
},
|
| 875 |
-
"
|
| 876 |
"content": "<|control107|>",
|
| 877 |
"lstrip": false,
|
| 878 |
"normalized": false,
|
|
@@ -880,7 +880,7 @@
|
|
| 880 |
"single_word": false,
|
| 881 |
"special": true
|
| 882 |
},
|
| 883 |
-
"
|
| 884 |
"content": "<|control108|>",
|
| 885 |
"lstrip": false,
|
| 886 |
"normalized": false,
|
|
@@ -888,7 +888,7 @@
|
|
| 888 |
"single_word": false,
|
| 889 |
"special": true
|
| 890 |
},
|
| 891 |
-
"
|
| 892 |
"content": "<|control109|>",
|
| 893 |
"lstrip": false,
|
| 894 |
"normalized": false,
|
|
@@ -896,7 +896,7 @@
|
|
| 896 |
"single_word": false,
|
| 897 |
"special": true
|
| 898 |
},
|
| 899 |
-
"
|
| 900 |
"content": "<|control110|>",
|
| 901 |
"lstrip": false,
|
| 902 |
"normalized": false,
|
|
@@ -904,7 +904,7 @@
|
|
| 904 |
"single_word": false,
|
| 905 |
"special": true
|
| 906 |
},
|
| 907 |
-
"
|
| 908 |
"content": "<|control111|>",
|
| 909 |
"lstrip": false,
|
| 910 |
"normalized": false,
|
|
@@ -912,7 +912,7 @@
|
|
| 912 |
"single_word": false,
|
| 913 |
"special": true
|
| 914 |
},
|
| 915 |
-
"
|
| 916 |
"content": "<|control112|>",
|
| 917 |
"lstrip": false,
|
| 918 |
"normalized": false,
|
|
@@ -920,7 +920,7 @@
|
|
| 920 |
"single_word": false,
|
| 921 |
"special": true
|
| 922 |
},
|
| 923 |
-
"
|
| 924 |
"content": "<|control113|>",
|
| 925 |
"lstrip": false,
|
| 926 |
"normalized": false,
|
|
@@ -928,7 +928,7 @@
|
|
| 928 |
"single_word": false,
|
| 929 |
"special": true
|
| 930 |
},
|
| 931 |
-
"
|
| 932 |
"content": "<|control114|>",
|
| 933 |
"lstrip": false,
|
| 934 |
"normalized": false,
|
|
@@ -936,7 +936,7 @@
|
|
| 936 |
"single_word": false,
|
| 937 |
"special": true
|
| 938 |
},
|
| 939 |
-
"
|
| 940 |
"content": "<|control115|>",
|
| 941 |
"lstrip": false,
|
| 942 |
"normalized": false,
|
|
@@ -944,7 +944,7 @@
|
|
| 944 |
"single_word": false,
|
| 945 |
"special": true
|
| 946 |
},
|
| 947 |
-
"
|
| 948 |
"content": "<|control116|>",
|
| 949 |
"lstrip": false,
|
| 950 |
"normalized": false,
|
|
@@ -952,7 +952,7 @@
|
|
| 952 |
"single_word": false,
|
| 953 |
"special": true
|
| 954 |
},
|
| 955 |
-
"
|
| 956 |
"content": "<|control117|>",
|
| 957 |
"lstrip": false,
|
| 958 |
"normalized": false,
|
|
@@ -960,7 +960,7 @@
|
|
| 960 |
"single_word": false,
|
| 961 |
"special": true
|
| 962 |
},
|
| 963 |
-
"
|
| 964 |
"content": "<|control118|>",
|
| 965 |
"lstrip": false,
|
| 966 |
"normalized": false,
|
|
@@ -968,7 +968,7 @@
|
|
| 968 |
"single_word": false,
|
| 969 |
"special": true
|
| 970 |
},
|
| 971 |
-
"
|
| 972 |
"content": "<|control119|>",
|
| 973 |
"lstrip": false,
|
| 974 |
"normalized": false,
|
|
@@ -976,7 +976,7 @@
|
|
| 976 |
"single_word": false,
|
| 977 |
"special": true
|
| 978 |
},
|
| 979 |
-
"
|
| 980 |
"content": "<|control120|>",
|
| 981 |
"lstrip": false,
|
| 982 |
"normalized": false,
|
|
@@ -984,7 +984,7 @@
|
|
| 984 |
"single_word": false,
|
| 985 |
"special": true
|
| 986 |
},
|
| 987 |
-
"
|
| 988 |
"content": "<|control121|>",
|
| 989 |
"lstrip": false,
|
| 990 |
"normalized": false,
|
|
@@ -992,7 +992,7 @@
|
|
| 992 |
"single_word": false,
|
| 993 |
"special": true
|
| 994 |
},
|
| 995 |
-
"
|
| 996 |
"content": "<|control122|>",
|
| 997 |
"lstrip": false,
|
| 998 |
"normalized": false,
|
|
@@ -1000,7 +1000,7 @@
|
|
| 1000 |
"single_word": false,
|
| 1001 |
"special": true
|
| 1002 |
},
|
| 1003 |
-
"
|
| 1004 |
"content": "<|control123|>",
|
| 1005 |
"lstrip": false,
|
| 1006 |
"normalized": false,
|
|
@@ -1008,7 +1008,7 @@
|
|
| 1008 |
"single_word": false,
|
| 1009 |
"special": true
|
| 1010 |
},
|
| 1011 |
-
"
|
| 1012 |
"content": "<|control124|>",
|
| 1013 |
"lstrip": false,
|
| 1014 |
"normalized": false,
|
|
@@ -1016,7 +1016,7 @@
|
|
| 1016 |
"single_word": false,
|
| 1017 |
"special": true
|
| 1018 |
},
|
| 1019 |
-
"
|
| 1020 |
"content": "<|control125|>",
|
| 1021 |
"lstrip": false,
|
| 1022 |
"normalized": false,
|
|
@@ -1025,8 +1025,141 @@
|
|
| 1025 |
"special": true
|
| 1026 |
}
|
| 1027 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1028 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 1029 |
"extra_special_tokens": {},
|
| 1030 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
| 1031 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 1032 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
"content": "<|pad|>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
|
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"1": {
|
| 12 |
"content": "<|separator|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
"content": "<|eos|>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"3": {
|
| 28 |
"content": "<|control1|>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"4": {
|
| 36 |
"content": "<|control2|>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
+
"5": {
|
| 44 |
"content": "<|control3|>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
|
|
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
+
"6": {
|
| 52 |
"content": "<|control4|>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
|
|
| 56 |
"single_word": false,
|
| 57 |
"special": true
|
| 58 |
},
|
| 59 |
+
"7": {
|
| 60 |
"content": "<|control5|>",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": false,
|
|
|
|
| 64 |
"single_word": false,
|
| 65 |
"special": true
|
| 66 |
},
|
| 67 |
+
"8": {
|
| 68 |
"content": "<|control6|>",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": false,
|
|
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
+
"9": {
|
| 76 |
"content": "<|control7|>",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
|
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": true
|
| 82 |
},
|
| 83 |
+
"10": {
|
| 84 |
"content": "<|control8|>",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": false,
|
|
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": true
|
| 90 |
},
|
| 91 |
+
"11": {
|
| 92 |
"content": "<|control9|>",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": false,
|
|
|
|
| 96 |
"single_word": false,
|
| 97 |
"special": true
|
| 98 |
},
|
| 99 |
+
"12": {
|
| 100 |
"content": "<|control10|>",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": false,
|
|
|
|
| 104 |
"single_word": false,
|
| 105 |
"special": true
|
| 106 |
},
|
| 107 |
+
"13": {
|
| 108 |
"content": "<|control11|>",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": false,
|
|
|
|
| 112 |
"single_word": false,
|
| 113 |
"special": true
|
| 114 |
},
|
| 115 |
+
"14": {
|
| 116 |
"content": "<|control12|>",
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": false,
|
|
|
|
| 120 |
"single_word": false,
|
| 121 |
"special": true
|
| 122 |
},
|
| 123 |
+
"15": {
|
| 124 |
"content": "<|control13|>",
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": false,
|
|
|
|
| 128 |
"single_word": false,
|
| 129 |
"special": true
|
| 130 |
},
|
| 131 |
+
"16": {
|
| 132 |
"content": "<|control14|>",
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": false,
|
|
|
|
| 136 |
"single_word": false,
|
| 137 |
"special": true
|
| 138 |
},
|
| 139 |
+
"17": {
|
| 140 |
"content": "<|control15|>",
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": false,
|
|
|
|
| 144 |
"single_word": false,
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
+
"18": {
|
| 148 |
"content": "<|control16|>",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
|
|
|
| 152 |
"single_word": false,
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
+
"19": {
|
| 156 |
"content": "<|control17|>",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
|
|
|
| 160 |
"single_word": false,
|
| 161 |
"special": true
|
| 162 |
},
|
| 163 |
+
"20": {
|
| 164 |
"content": "<|control18|>",
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": false,
|
|
|
|
| 168 |
"single_word": false,
|
| 169 |
"special": true
|
| 170 |
},
|
| 171 |
+
"21": {
|
| 172 |
"content": "<|control19|>",
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": false,
|
|
|
|
| 176 |
"single_word": false,
|
| 177 |
"special": true
|
| 178 |
},
|
| 179 |
+
"22": {
|
| 180 |
"content": "<|control20|>",
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": false,
|
|
|
|
| 184 |
"single_word": false,
|
| 185 |
"special": true
|
| 186 |
},
|
| 187 |
+
"23": {
|
| 188 |
"content": "<|control21|>",
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": false,
|
|
|
|
| 192 |
"single_word": false,
|
| 193 |
"special": true
|
| 194 |
},
|
| 195 |
+
"24": {
|
| 196 |
"content": "<|control22|>",
|
| 197 |
"lstrip": false,
|
| 198 |
"normalized": false,
|
|
|
|
| 200 |
"single_word": false,
|
| 201 |
"special": true
|
| 202 |
},
|
| 203 |
+
"25": {
|
| 204 |
"content": "<|control23|>",
|
| 205 |
"lstrip": false,
|
| 206 |
"normalized": false,
|
|
|
|
| 208 |
"single_word": false,
|
| 209 |
"special": true
|
| 210 |
},
|
| 211 |
+
"26": {
|
| 212 |
"content": "<|control24|>",
|
| 213 |
"lstrip": false,
|
| 214 |
"normalized": false,
|
|
|
|
| 216 |
"single_word": false,
|
| 217 |
"special": true
|
| 218 |
},
|
| 219 |
+
"27": {
|
| 220 |
"content": "<|control25|>",
|
| 221 |
"lstrip": false,
|
| 222 |
"normalized": false,
|
|
|
|
| 224 |
"single_word": false,
|
| 225 |
"special": true
|
| 226 |
},
|
| 227 |
+
"28": {
|
| 228 |
"content": "<|control26|>",
|
| 229 |
"lstrip": false,
|
| 230 |
"normalized": false,
|
|
|
|
| 232 |
"single_word": false,
|
| 233 |
"special": true
|
| 234 |
},
|
| 235 |
+
"29": {
|
| 236 |
"content": "<|control27|>",
|
| 237 |
"lstrip": false,
|
| 238 |
"normalized": false,
|
|
|
|
| 240 |
"single_word": false,
|
| 241 |
"special": true
|
| 242 |
},
|
| 243 |
+
"30": {
|
| 244 |
"content": "<|control28|>",
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": false,
|
|
|
|
| 248 |
"single_word": false,
|
| 249 |
"special": true
|
| 250 |
},
|
| 251 |
+
"31": {
|
| 252 |
"content": "<|control29|>",
|
| 253 |
"lstrip": false,
|
| 254 |
"normalized": false,
|
|
|
|
| 256 |
"single_word": false,
|
| 257 |
"special": true
|
| 258 |
},
|
| 259 |
+
"32": {
|
| 260 |
"content": "<|control30|>",
|
| 261 |
"lstrip": false,
|
| 262 |
"normalized": false,
|
|
|
|
| 264 |
"single_word": false,
|
| 265 |
"special": true
|
| 266 |
},
|
| 267 |
+
"33": {
|
| 268 |
"content": "<|control31|>",
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": false,
|
|
|
|
| 272 |
"single_word": false,
|
| 273 |
"special": true
|
| 274 |
},
|
| 275 |
+
"34": {
|
| 276 |
"content": "<|control32|>",
|
| 277 |
"lstrip": false,
|
| 278 |
"normalized": false,
|
|
|
|
| 280 |
"single_word": false,
|
| 281 |
"special": true
|
| 282 |
},
|
| 283 |
+
"35": {
|
| 284 |
"content": "<|control33|>",
|
| 285 |
"lstrip": false,
|
| 286 |
"normalized": false,
|
|
|
|
| 288 |
"single_word": false,
|
| 289 |
"special": true
|
| 290 |
},
|
| 291 |
+
"36": {
|
| 292 |
"content": "<|control34|>",
|
| 293 |
"lstrip": false,
|
| 294 |
"normalized": false,
|
|
|
|
| 296 |
"single_word": false,
|
| 297 |
"special": true
|
| 298 |
},
|
| 299 |
+
"37": {
|
| 300 |
"content": "<|control35|>",
|
| 301 |
"lstrip": false,
|
| 302 |
"normalized": false,
|
|
|
|
| 304 |
"single_word": false,
|
| 305 |
"special": true
|
| 306 |
},
|
| 307 |
+
"38": {
|
| 308 |
"content": "<|control36|>",
|
| 309 |
"lstrip": false,
|
| 310 |
"normalized": false,
|
|
|
|
| 312 |
"single_word": false,
|
| 313 |
"special": true
|
| 314 |
},
|
| 315 |
+
"39": {
|
| 316 |
"content": "<|control37|>",
|
| 317 |
"lstrip": false,
|
| 318 |
"normalized": false,
|
|
|
|
| 320 |
"single_word": false,
|
| 321 |
"special": true
|
| 322 |
},
|
| 323 |
+
"40": {
|
| 324 |
"content": "<|control38|>",
|
| 325 |
"lstrip": false,
|
| 326 |
"normalized": false,
|
|
|
|
| 328 |
"single_word": false,
|
| 329 |
"special": true
|
| 330 |
},
|
| 331 |
+
"41": {
|
| 332 |
"content": "<|control39|>",
|
| 333 |
"lstrip": false,
|
| 334 |
"normalized": false,
|
|
|
|
| 336 |
"single_word": false,
|
| 337 |
"special": true
|
| 338 |
},
|
| 339 |
+
"42": {
|
| 340 |
"content": "<|control40|>",
|
| 341 |
"lstrip": false,
|
| 342 |
"normalized": false,
|
|
|
|
| 344 |
"single_word": false,
|
| 345 |
"special": true
|
| 346 |
},
|
| 347 |
+
"43": {
|
| 348 |
"content": "<|control41|>",
|
| 349 |
"lstrip": false,
|
| 350 |
"normalized": false,
|
|
|
|
| 352 |
"single_word": false,
|
| 353 |
"special": true
|
| 354 |
},
|
| 355 |
+
"44": {
|
| 356 |
"content": "<|control42|>",
|
| 357 |
"lstrip": false,
|
| 358 |
"normalized": false,
|
|
|
|
| 360 |
"single_word": false,
|
| 361 |
"special": true
|
| 362 |
},
|
| 363 |
+
"45": {
|
| 364 |
"content": "<|control43|>",
|
| 365 |
"lstrip": false,
|
| 366 |
"normalized": false,
|
|
|
|
| 368 |
"single_word": false,
|
| 369 |
"special": true
|
| 370 |
},
|
| 371 |
+
"46": {
|
| 372 |
"content": "<|control44|>",
|
| 373 |
"lstrip": false,
|
| 374 |
"normalized": false,
|
|
|
|
| 376 |
"single_word": false,
|
| 377 |
"special": true
|
| 378 |
},
|
| 379 |
+
"47": {
|
| 380 |
"content": "<|control45|>",
|
| 381 |
"lstrip": false,
|
| 382 |
"normalized": false,
|
|
|
|
| 384 |
"single_word": false,
|
| 385 |
"special": true
|
| 386 |
},
|
| 387 |
+
"48": {
|
| 388 |
"content": "<|control46|>",
|
| 389 |
"lstrip": false,
|
| 390 |
"normalized": false,
|
|
|
|
| 392 |
"single_word": false,
|
| 393 |
"special": true
|
| 394 |
},
|
| 395 |
+
"49": {
|
| 396 |
"content": "<|control47|>",
|
| 397 |
"lstrip": false,
|
| 398 |
"normalized": false,
|
|
|
|
| 400 |
"single_word": false,
|
| 401 |
"special": true
|
| 402 |
},
|
| 403 |
+
"50": {
|
| 404 |
"content": "<|control48|>",
|
| 405 |
"lstrip": false,
|
| 406 |
"normalized": false,
|
|
|
|
| 408 |
"single_word": false,
|
| 409 |
"special": true
|
| 410 |
},
|
| 411 |
+
"51": {
|
| 412 |
"content": "<|control49|>",
|
| 413 |
"lstrip": false,
|
| 414 |
"normalized": false,
|
|
|
|
| 416 |
"single_word": false,
|
| 417 |
"special": true
|
| 418 |
},
|
| 419 |
+
"52": {
|
| 420 |
"content": "<|control50|>",
|
| 421 |
"lstrip": false,
|
| 422 |
"normalized": false,
|
|
|
|
| 424 |
"single_word": false,
|
| 425 |
"special": true
|
| 426 |
},
|
| 427 |
+
"53": {
|
| 428 |
"content": "<|control51|>",
|
| 429 |
"lstrip": false,
|
| 430 |
"normalized": false,
|
|
|
|
| 432 |
"single_word": false,
|
| 433 |
"special": true
|
| 434 |
},
|
| 435 |
+
"54": {
|
| 436 |
"content": "<|control52|>",
|
| 437 |
"lstrip": false,
|
| 438 |
"normalized": false,
|
|
|
|
| 440 |
"single_word": false,
|
| 441 |
"special": true
|
| 442 |
},
|
| 443 |
+
"55": {
|
| 444 |
"content": "<|control53|>",
|
| 445 |
"lstrip": false,
|
| 446 |
"normalized": false,
|
|
|
|
| 448 |
"single_word": false,
|
| 449 |
"special": true
|
| 450 |
},
|
| 451 |
+
"56": {
|
| 452 |
"content": "<|control54|>",
|
| 453 |
"lstrip": false,
|
| 454 |
"normalized": false,
|
|
|
|
| 456 |
"single_word": false,
|
| 457 |
"special": true
|
| 458 |
},
|
| 459 |
+
"57": {
|
| 460 |
"content": "<|control55|>",
|
| 461 |
"lstrip": false,
|
| 462 |
"normalized": false,
|
|
|
|
| 464 |
"single_word": false,
|
| 465 |
"special": true
|
| 466 |
},
|
| 467 |
+
"58": {
|
| 468 |
"content": "<|control56|>",
|
| 469 |
"lstrip": false,
|
| 470 |
"normalized": false,
|
|
|
|
| 472 |
"single_word": false,
|
| 473 |
"special": true
|
| 474 |
},
|
| 475 |
+
"59": {
|
| 476 |
"content": "<|control57|>",
|
| 477 |
"lstrip": false,
|
| 478 |
"normalized": false,
|
|
|
|
| 480 |
"single_word": false,
|
| 481 |
"special": true
|
| 482 |
},
|
| 483 |
+
"60": {
|
| 484 |
"content": "<|control58|>",
|
| 485 |
"lstrip": false,
|
| 486 |
"normalized": false,
|
|
|
|
| 488 |
"single_word": false,
|
| 489 |
"special": true
|
| 490 |
},
|
| 491 |
+
"61": {
|
| 492 |
"content": "<|control59|>",
|
| 493 |
"lstrip": false,
|
| 494 |
"normalized": false,
|
|
|
|
| 496 |
"single_word": false,
|
| 497 |
"special": true
|
| 498 |
},
|
| 499 |
+
"62": {
|
| 500 |
"content": "<|control60|>",
|
| 501 |
"lstrip": false,
|
| 502 |
"normalized": false,
|
|
|
|
| 504 |
"single_word": false,
|
| 505 |
"special": true
|
| 506 |
},
|
| 507 |
+
"63": {
|
| 508 |
"content": "<|control61|>",
|
| 509 |
"lstrip": false,
|
| 510 |
"normalized": false,
|
|
|
|
| 512 |
"single_word": false,
|
| 513 |
"special": true
|
| 514 |
},
|
| 515 |
+
"64": {
|
| 516 |
"content": "<|control62|>",
|
| 517 |
"lstrip": false,
|
| 518 |
"normalized": false,
|
|
|
|
| 520 |
"single_word": false,
|
| 521 |
"special": true
|
| 522 |
},
|
| 523 |
+
"65": {
|
| 524 |
"content": "<|control63|>",
|
| 525 |
"lstrip": false,
|
| 526 |
"normalized": false,
|
|
|
|
| 528 |
"single_word": false,
|
| 529 |
"special": true
|
| 530 |
},
|
| 531 |
+
"66": {
|
| 532 |
"content": "<|control64|>",
|
| 533 |
"lstrip": false,
|
| 534 |
"normalized": false,
|
|
|
|
| 536 |
"single_word": false,
|
| 537 |
"special": true
|
| 538 |
},
|
| 539 |
+
"67": {
|
| 540 |
"content": "<|control65|>",
|
| 541 |
"lstrip": false,
|
| 542 |
"normalized": false,
|
|
|
|
| 544 |
"single_word": false,
|
| 545 |
"special": true
|
| 546 |
},
|
| 547 |
+
"68": {
|
| 548 |
"content": "<|control66|>",
|
| 549 |
"lstrip": false,
|
| 550 |
"normalized": false,
|
|
|
|
| 552 |
"single_word": false,
|
| 553 |
"special": true
|
| 554 |
},
|
| 555 |
+
"69": {
|
| 556 |
"content": "<|control67|>",
|
| 557 |
"lstrip": false,
|
| 558 |
"normalized": false,
|
|
|
|
| 560 |
"single_word": false,
|
| 561 |
"special": true
|
| 562 |
},
|
| 563 |
+
"70": {
|
| 564 |
"content": "<|control68|>",
|
| 565 |
"lstrip": false,
|
| 566 |
"normalized": false,
|
|
|
|
| 568 |
"single_word": false,
|
| 569 |
"special": true
|
| 570 |
},
|
| 571 |
+
"71": {
|
| 572 |
"content": "<|control69|>",
|
| 573 |
"lstrip": false,
|
| 574 |
"normalized": false,
|
|
|
|
| 576 |
"single_word": false,
|
| 577 |
"special": true
|
| 578 |
},
|
| 579 |
+
"72": {
|
| 580 |
"content": "<|control70|>",
|
| 581 |
"lstrip": false,
|
| 582 |
"normalized": false,
|
|
|
|
| 584 |
"single_word": false,
|
| 585 |
"special": true
|
| 586 |
},
|
| 587 |
+
"73": {
|
| 588 |
"content": "<|control71|>",
|
| 589 |
"lstrip": false,
|
| 590 |
"normalized": false,
|
|
|
|
| 592 |
"single_word": false,
|
| 593 |
"special": true
|
| 594 |
},
|
| 595 |
+
"74": {
|
| 596 |
"content": "<|control72|>",
|
| 597 |
"lstrip": false,
|
| 598 |
"normalized": false,
|
|
|
|
| 600 |
"single_word": false,
|
| 601 |
"special": true
|
| 602 |
},
|
| 603 |
+
"75": {
|
| 604 |
"content": "<|control73|>",
|
| 605 |
"lstrip": false,
|
| 606 |
"normalized": false,
|
|
|
|
| 608 |
"single_word": false,
|
| 609 |
"special": true
|
| 610 |
},
|
| 611 |
+
"76": {
|
| 612 |
"content": "<|control74|>",
|
| 613 |
"lstrip": false,
|
| 614 |
"normalized": false,
|
|
|
|
| 616 |
"single_word": false,
|
| 617 |
"special": true
|
| 618 |
},
|
| 619 |
+
"77": {
|
| 620 |
"content": "<|control75|>",
|
| 621 |
"lstrip": false,
|
| 622 |
"normalized": false,
|
|
|
|
| 624 |
"single_word": false,
|
| 625 |
"special": true
|
| 626 |
},
|
| 627 |
+
"78": {
|
| 628 |
"content": "<|control76|>",
|
| 629 |
"lstrip": false,
|
| 630 |
"normalized": false,
|
|
|
|
| 632 |
"single_word": false,
|
| 633 |
"special": true
|
| 634 |
},
|
| 635 |
+
"79": {
|
| 636 |
"content": "<|control77|>",
|
| 637 |
"lstrip": false,
|
| 638 |
"normalized": false,
|
|
|
|
| 640 |
"single_word": false,
|
| 641 |
"special": true
|
| 642 |
},
|
| 643 |
+
"80": {
|
| 644 |
"content": "<|control78|>",
|
| 645 |
"lstrip": false,
|
| 646 |
"normalized": false,
|
|
|
|
| 648 |
"single_word": false,
|
| 649 |
"special": true
|
| 650 |
},
|
| 651 |
+
"81": {
|
| 652 |
"content": "<|control79|>",
|
| 653 |
"lstrip": false,
|
| 654 |
"normalized": false,
|
|
|
|
| 656 |
"single_word": false,
|
| 657 |
"special": true
|
| 658 |
},
|
| 659 |
+
"82": {
|
| 660 |
"content": "<|control80|>",
|
| 661 |
"lstrip": false,
|
| 662 |
"normalized": false,
|
|
|
|
| 664 |
"single_word": false,
|
| 665 |
"special": true
|
| 666 |
},
|
| 667 |
+
"83": {
|
| 668 |
"content": "<|control81|>",
|
| 669 |
"lstrip": false,
|
| 670 |
"normalized": false,
|
|
|
|
| 672 |
"single_word": false,
|
| 673 |
"special": true
|
| 674 |
},
|
| 675 |
+
"84": {
|
| 676 |
"content": "<|control82|>",
|
| 677 |
"lstrip": false,
|
| 678 |
"normalized": false,
|
|
|
|
| 680 |
"single_word": false,
|
| 681 |
"special": true
|
| 682 |
},
|
| 683 |
+
"85": {
|
| 684 |
"content": "<|control83|>",
|
| 685 |
"lstrip": false,
|
| 686 |
"normalized": false,
|
|
|
|
| 688 |
"single_word": false,
|
| 689 |
"special": true
|
| 690 |
},
|
| 691 |
+
"86": {
|
| 692 |
"content": "<|control84|>",
|
| 693 |
"lstrip": false,
|
| 694 |
"normalized": false,
|
|
|
|
| 696 |
"single_word": false,
|
| 697 |
"special": true
|
| 698 |
},
|
| 699 |
+
"87": {
|
| 700 |
"content": "<|control85|>",
|
| 701 |
"lstrip": false,
|
| 702 |
"normalized": false,
|
|
|
|
| 704 |
"single_word": false,
|
| 705 |
"special": true
|
| 706 |
},
|
| 707 |
+
"88": {
|
| 708 |
"content": "<|control86|>",
|
| 709 |
"lstrip": false,
|
| 710 |
"normalized": false,
|
|
|
|
| 712 |
"single_word": false,
|
| 713 |
"special": true
|
| 714 |
},
|
| 715 |
+
"89": {
|
| 716 |
"content": "<|control87|>",
|
| 717 |
"lstrip": false,
|
| 718 |
"normalized": false,
|
|
|
|
| 720 |
"single_word": false,
|
| 721 |
"special": true
|
| 722 |
},
|
| 723 |
+
"90": {
|
| 724 |
"content": "<|control88|>",
|
| 725 |
"lstrip": false,
|
| 726 |
"normalized": false,
|
|
|
|
| 728 |
"single_word": false,
|
| 729 |
"special": true
|
| 730 |
},
|
| 731 |
+
"91": {
|
| 732 |
"content": "<|control89|>",
|
| 733 |
"lstrip": false,
|
| 734 |
"normalized": false,
|
|
|
|
| 736 |
"single_word": false,
|
| 737 |
"special": true
|
| 738 |
},
|
| 739 |
+
"92": {
|
| 740 |
"content": "<|control90|>",
|
| 741 |
"lstrip": false,
|
| 742 |
"normalized": false,
|
|
|
|
| 744 |
"single_word": false,
|
| 745 |
"special": true
|
| 746 |
},
|
| 747 |
+
"93": {
|
| 748 |
"content": "<|control91|>",
|
| 749 |
"lstrip": false,
|
| 750 |
"normalized": false,
|
|
|
|
| 752 |
"single_word": false,
|
| 753 |
"special": true
|
| 754 |
},
|
| 755 |
+
"94": {
|
| 756 |
"content": "<|control92|>",
|
| 757 |
"lstrip": false,
|
| 758 |
"normalized": false,
|
|
|
|
| 760 |
"single_word": false,
|
| 761 |
"special": true
|
| 762 |
},
|
| 763 |
+
"95": {
|
| 764 |
"content": "<|control93|>",
|
| 765 |
"lstrip": false,
|
| 766 |
"normalized": false,
|
|
|
|
| 768 |
"single_word": false,
|
| 769 |
"special": true
|
| 770 |
},
|
| 771 |
+
"96": {
|
| 772 |
"content": "<|control94|>",
|
| 773 |
"lstrip": false,
|
| 774 |
"normalized": false,
|
|
|
|
| 776 |
"single_word": false,
|
| 777 |
"special": true
|
| 778 |
},
|
| 779 |
+
"97": {
|
| 780 |
"content": "<|control95|>",
|
| 781 |
"lstrip": false,
|
| 782 |
"normalized": false,
|
|
|
|
| 784 |
"single_word": false,
|
| 785 |
"special": true
|
| 786 |
},
|
| 787 |
+
"98": {
|
| 788 |
"content": "<|control96|>",
|
| 789 |
"lstrip": false,
|
| 790 |
"normalized": false,
|
|
|
|
| 792 |
"single_word": false,
|
| 793 |
"special": true
|
| 794 |
},
|
| 795 |
+
"99": {
|
| 796 |
"content": "<|control97|>",
|
| 797 |
"lstrip": false,
|
| 798 |
"normalized": false,
|
|
|
|
| 800 |
"single_word": false,
|
| 801 |
"special": true
|
| 802 |
},
|
| 803 |
+
"100": {
|
| 804 |
"content": "<|control98|>",
|
| 805 |
"lstrip": false,
|
| 806 |
"normalized": false,
|
|
|
|
| 808 |
"single_word": false,
|
| 809 |
"special": true
|
| 810 |
},
|
| 811 |
+
"101": {
|
| 812 |
"content": "<|control99|>",
|
| 813 |
"lstrip": false,
|
| 814 |
"normalized": false,
|
|
|
|
| 816 |
"single_word": false,
|
| 817 |
"special": true
|
| 818 |
},
|
| 819 |
+
"102": {
|
| 820 |
"content": "<|control100|>",
|
| 821 |
"lstrip": false,
|
| 822 |
"normalized": false,
|
|
|
|
| 824 |
"single_word": false,
|
| 825 |
"special": true
|
| 826 |
},
|
| 827 |
+
"103": {
|
| 828 |
"content": "<|control101|>",
|
| 829 |
"lstrip": false,
|
| 830 |
"normalized": false,
|
|
|
|
| 832 |
"single_word": false,
|
| 833 |
"special": true
|
| 834 |
},
|
| 835 |
+
"104": {
|
| 836 |
"content": "<|control102|>",
|
| 837 |
"lstrip": false,
|
| 838 |
"normalized": false,
|
|
|
|
| 840 |
"single_word": false,
|
| 841 |
"special": true
|
| 842 |
},
|
| 843 |
+
"105": {
|
| 844 |
"content": "<|control103|>",
|
| 845 |
"lstrip": false,
|
| 846 |
"normalized": false,
|
|
|
|
| 848 |
"single_word": false,
|
| 849 |
"special": true
|
| 850 |
},
|
| 851 |
+
"106": {
|
| 852 |
"content": "<|control104|>",
|
| 853 |
"lstrip": false,
|
| 854 |
"normalized": false,
|
|
|
|
| 856 |
"single_word": false,
|
| 857 |
"special": true
|
| 858 |
},
|
| 859 |
+
"107": {
|
| 860 |
"content": "<|control105|>",
|
| 861 |
"lstrip": false,
|
| 862 |
"normalized": false,
|
|
|
|
| 864 |
"single_word": false,
|
| 865 |
"special": true
|
| 866 |
},
|
| 867 |
+
"108": {
|
| 868 |
"content": "<|control106|>",
|
| 869 |
"lstrip": false,
|
| 870 |
"normalized": false,
|
|
|
|
| 872 |
"single_word": false,
|
| 873 |
"special": true
|
| 874 |
},
|
| 875 |
+
"109": {
|
| 876 |
"content": "<|control107|>",
|
| 877 |
"lstrip": false,
|
| 878 |
"normalized": false,
|
|
|
|
| 880 |
"single_word": false,
|
| 881 |
"special": true
|
| 882 |
},
|
| 883 |
+
"110": {
|
| 884 |
"content": "<|control108|>",
|
| 885 |
"lstrip": false,
|
| 886 |
"normalized": false,
|
|
|
|
| 888 |
"single_word": false,
|
| 889 |
"special": true
|
| 890 |
},
|
| 891 |
+
"111": {
|
| 892 |
"content": "<|control109|>",
|
| 893 |
"lstrip": false,
|
| 894 |
"normalized": false,
|
|
|
|
| 896 |
"single_word": false,
|
| 897 |
"special": true
|
| 898 |
},
|
| 899 |
+
"112": {
|
| 900 |
"content": "<|control110|>",
|
| 901 |
"lstrip": false,
|
| 902 |
"normalized": false,
|
|
|
|
| 904 |
"single_word": false,
|
| 905 |
"special": true
|
| 906 |
},
|
| 907 |
+
"113": {
|
| 908 |
"content": "<|control111|>",
|
| 909 |
"lstrip": false,
|
| 910 |
"normalized": false,
|
|
|
|
| 912 |
"single_word": false,
|
| 913 |
"special": true
|
| 914 |
},
|
| 915 |
+
"114": {
|
| 916 |
"content": "<|control112|>",
|
| 917 |
"lstrip": false,
|
| 918 |
"normalized": false,
|
|
|
|
| 920 |
"single_word": false,
|
| 921 |
"special": true
|
| 922 |
},
|
| 923 |
+
"115": {
|
| 924 |
"content": "<|control113|>",
|
| 925 |
"lstrip": false,
|
| 926 |
"normalized": false,
|
|
|
|
| 928 |
"single_word": false,
|
| 929 |
"special": true
|
| 930 |
},
|
| 931 |
+
"116": {
|
| 932 |
"content": "<|control114|>",
|
| 933 |
"lstrip": false,
|
| 934 |
"normalized": false,
|
|
|
|
| 936 |
"single_word": false,
|
| 937 |
"special": true
|
| 938 |
},
|
| 939 |
+
"117": {
|
| 940 |
"content": "<|control115|>",
|
| 941 |
"lstrip": false,
|
| 942 |
"normalized": false,
|
|
|
|
| 944 |
"single_word": false,
|
| 945 |
"special": true
|
| 946 |
},
|
| 947 |
+
"118": {
|
| 948 |
"content": "<|control116|>",
|
| 949 |
"lstrip": false,
|
| 950 |
"normalized": false,
|
|
|
|
| 952 |
"single_word": false,
|
| 953 |
"special": true
|
| 954 |
},
|
| 955 |
+
"119": {
|
| 956 |
"content": "<|control117|>",
|
| 957 |
"lstrip": false,
|
| 958 |
"normalized": false,
|
|
|
|
| 960 |
"single_word": false,
|
| 961 |
"special": true
|
| 962 |
},
|
| 963 |
+
"120": {
|
| 964 |
"content": "<|control118|>",
|
| 965 |
"lstrip": false,
|
| 966 |
"normalized": false,
|
|
|
|
| 968 |
"single_word": false,
|
| 969 |
"special": true
|
| 970 |
},
|
| 971 |
+
"121": {
|
| 972 |
"content": "<|control119|>",
|
| 973 |
"lstrip": false,
|
| 974 |
"normalized": false,
|
|
|
|
| 976 |
"single_word": false,
|
| 977 |
"special": true
|
| 978 |
},
|
| 979 |
+
"122": {
|
| 980 |
"content": "<|control120|>",
|
| 981 |
"lstrip": false,
|
| 982 |
"normalized": false,
|
|
|
|
| 984 |
"single_word": false,
|
| 985 |
"special": true
|
| 986 |
},
|
| 987 |
+
"123": {
|
| 988 |
"content": "<|control121|>",
|
| 989 |
"lstrip": false,
|
| 990 |
"normalized": false,
|
|
|
|
| 992 |
"single_word": false,
|
| 993 |
"special": true
|
| 994 |
},
|
| 995 |
+
"124": {
|
| 996 |
"content": "<|control122|>",
|
| 997 |
"lstrip": false,
|
| 998 |
"normalized": false,
|
|
|
|
| 1000 |
"single_word": false,
|
| 1001 |
"special": true
|
| 1002 |
},
|
| 1003 |
+
"125": {
|
| 1004 |
"content": "<|control123|>",
|
| 1005 |
"lstrip": false,
|
| 1006 |
"normalized": false,
|
|
|
|
| 1008 |
"single_word": false,
|
| 1009 |
"special": true
|
| 1010 |
},
|
| 1011 |
+
"126": {
|
| 1012 |
"content": "<|control124|>",
|
| 1013 |
"lstrip": false,
|
| 1014 |
"normalized": false,
|
|
|
|
| 1016 |
"single_word": false,
|
| 1017 |
"special": true
|
| 1018 |
},
|
| 1019 |
+
"127": {
|
| 1020 |
"content": "<|control125|>",
|
| 1021 |
"lstrip": false,
|
| 1022 |
"normalized": false,
|
|
|
|
| 1025 |
"special": true
|
| 1026 |
}
|
| 1027 |
},
|
| 1028 |
+
"additional_special_tokens": [
|
| 1029 |
+
"<|pad|>",
|
| 1030 |
+
"<|separator|>",
|
| 1031 |
+
"<|eos|>",
|
| 1032 |
+
"<|control1|>",
|
| 1033 |
+
"<|control2|>",
|
| 1034 |
+
"<|control3|>",
|
| 1035 |
+
"<|control4|>",
|
| 1036 |
+
"<|control5|>",
|
| 1037 |
+
"<|control6|>",
|
| 1038 |
+
"<|control7|>",
|
| 1039 |
+
"<|control8|>",
|
| 1040 |
+
"<|control9|>",
|
| 1041 |
+
"<|control10|>",
|
| 1042 |
+
"<|control11|>",
|
| 1043 |
+
"<|control12|>",
|
| 1044 |
+
"<|control13|>",
|
| 1045 |
+
"<|control14|>",
|
| 1046 |
+
"<|control15|>",
|
| 1047 |
+
"<|control16|>",
|
| 1048 |
+
"<|control17|>",
|
| 1049 |
+
"<|control18|>",
|
| 1050 |
+
"<|control19|>",
|
| 1051 |
+
"<|control20|>",
|
| 1052 |
+
"<|control21|>",
|
| 1053 |
+
"<|control22|>",
|
| 1054 |
+
"<|control23|>",
|
| 1055 |
+
"<|control24|>",
|
| 1056 |
+
"<|control25|>",
|
| 1057 |
+
"<|control26|>",
|
| 1058 |
+
"<|control27|>",
|
| 1059 |
+
"<|control28|>",
|
| 1060 |
+
"<|control29|>",
|
| 1061 |
+
"<|control30|>",
|
| 1062 |
+
"<|control31|>",
|
| 1063 |
+
"<|control32|>",
|
| 1064 |
+
"<|control33|>",
|
| 1065 |
+
"<|control34|>",
|
| 1066 |
+
"<|control35|>",
|
| 1067 |
+
"<|control36|>",
|
| 1068 |
+
"<|control37|>",
|
| 1069 |
+
"<|control38|>",
|
| 1070 |
+
"<|control39|>",
|
| 1071 |
+
"<|control40|>",
|
| 1072 |
+
"<|control41|>",
|
| 1073 |
+
"<|control42|>",
|
| 1074 |
+
"<|control43|>",
|
| 1075 |
+
"<|control44|>",
|
| 1076 |
+
"<|control45|>",
|
| 1077 |
+
"<|control46|>",
|
| 1078 |
+
"<|control47|>",
|
| 1079 |
+
"<|control48|>",
|
| 1080 |
+
"<|control49|>",
|
| 1081 |
+
"<|control50|>",
|
| 1082 |
+
"<|control51|>",
|
| 1083 |
+
"<|control52|>",
|
| 1084 |
+
"<|control53|>",
|
| 1085 |
+
"<|control54|>",
|
| 1086 |
+
"<|control55|>",
|
| 1087 |
+
"<|control56|>",
|
| 1088 |
+
"<|control57|>",
|
| 1089 |
+
"<|control58|>",
|
| 1090 |
+
"<|control59|>",
|
| 1091 |
+
"<|control60|>",
|
| 1092 |
+
"<|control61|>",
|
| 1093 |
+
"<|control62|>",
|
| 1094 |
+
"<|control63|>",
|
| 1095 |
+
"<|control64|>",
|
| 1096 |
+
"<|control65|>",
|
| 1097 |
+
"<|control66|>",
|
| 1098 |
+
"<|control67|>",
|
| 1099 |
+
"<|control68|>",
|
| 1100 |
+
"<|control69|>",
|
| 1101 |
+
"<|control70|>",
|
| 1102 |
+
"<|control71|>",
|
| 1103 |
+
"<|control72|>",
|
| 1104 |
+
"<|control73|>",
|
| 1105 |
+
"<|control74|>",
|
| 1106 |
+
"<|control75|>",
|
| 1107 |
+
"<|control76|>",
|
| 1108 |
+
"<|control77|>",
|
| 1109 |
+
"<|control78|>",
|
| 1110 |
+
"<|control79|>",
|
| 1111 |
+
"<|control80|>",
|
| 1112 |
+
"<|control81|>",
|
| 1113 |
+
"<|control82|>",
|
| 1114 |
+
"<|control83|>",
|
| 1115 |
+
"<|control84|>",
|
| 1116 |
+
"<|control85|>",
|
| 1117 |
+
"<|control86|>",
|
| 1118 |
+
"<|control87|>",
|
| 1119 |
+
"<|control88|>",
|
| 1120 |
+
"<|control89|>",
|
| 1121 |
+
"<|control90|>",
|
| 1122 |
+
"<|control91|>",
|
| 1123 |
+
"<|control92|>",
|
| 1124 |
+
"<|control93|>",
|
| 1125 |
+
"<|control94|>",
|
| 1126 |
+
"<|control95|>",
|
| 1127 |
+
"<|control96|>",
|
| 1128 |
+
"<|control97|>",
|
| 1129 |
+
"<|control98|>",
|
| 1130 |
+
"<|control99|>",
|
| 1131 |
+
"<|control100|>",
|
| 1132 |
+
"<|control101|>",
|
| 1133 |
+
"<|control102|>",
|
| 1134 |
+
"<|control103|>",
|
| 1135 |
+
"<|control104|>",
|
| 1136 |
+
"<|control105|>",
|
| 1137 |
+
"<|control106|>",
|
| 1138 |
+
"<|control107|>",
|
| 1139 |
+
"<|control108|>",
|
| 1140 |
+
"<|control109|>",
|
| 1141 |
+
"<|control110|>",
|
| 1142 |
+
"<|control111|>",
|
| 1143 |
+
"<|control112|>",
|
| 1144 |
+
"<|control113|>",
|
| 1145 |
+
"<|control114|>",
|
| 1146 |
+
"<|control115|>",
|
| 1147 |
+
"<|control116|>",
|
| 1148 |
+
"<|control117|>",
|
| 1149 |
+
"<|control118|>",
|
| 1150 |
+
"<|control119|>",
|
| 1151 |
+
"<|control120|>",
|
| 1152 |
+
"<|control121|>",
|
| 1153 |
+
"<|control122|>",
|
| 1154 |
+
"<|control123|>",
|
| 1155 |
+
"<|control124|>",
|
| 1156 |
+
"<|control125|>"
|
| 1157 |
+
],
|
| 1158 |
"clean_up_tokenization_spaces": false,
|
| 1159 |
+
"eos_token": "<|eos|>",
|
| 1160 |
"extra_special_tokens": {},
|
| 1161 |
"model_max_length": 1000000000000000019884624838656,
|
| 1162 |
+
"pad_token": "<|pad|>",
|
| 1163 |
+
"sep_token": "<|separator|>",
|
| 1164 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 1165 |
}
|