Upload special_tokens_map.json with huggingface_hub
Browse files- special_tokens_map.json +288 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|begin_of_text|>",
|
| 4 |
+
"<|end_of_text|>",
|
| 5 |
+
"<|reserved_special_token_0|>",
|
| 6 |
+
"<|reserved_special_token_1|>",
|
| 7 |
+
"<|reserved_special_token_2|>",
|
| 8 |
+
"<|reserved_special_token_3|>",
|
| 9 |
+
"<|start_header_id|>",
|
| 10 |
+
"<|end_header_id|>",
|
| 11 |
+
"<|reserved_special_token_4|>",
|
| 12 |
+
"<|eot_id|>",
|
| 13 |
+
"<|reserved_special_token_5|>",
|
| 14 |
+
"<|reserved_special_token_6|>",
|
| 15 |
+
"<|reserved_special_token_7|>",
|
| 16 |
+
"<|reserved_special_token_8|>",
|
| 17 |
+
"<|reserved_special_token_9|>",
|
| 18 |
+
"<|reserved_special_token_10|>",
|
| 19 |
+
"<|reserved_special_token_11|>",
|
| 20 |
+
"<|reserved_special_token_12|>",
|
| 21 |
+
"<|reserved_special_token_13|>",
|
| 22 |
+
"<|reserved_special_token_14|>",
|
| 23 |
+
"<|reserved_special_token_15|>",
|
| 24 |
+
"<|reserved_special_token_16|>",
|
| 25 |
+
"<|reserved_special_token_17|>",
|
| 26 |
+
"<|reserved_special_token_18|>",
|
| 27 |
+
"<|reserved_special_token_19|>",
|
| 28 |
+
"<|reserved_special_token_20|>",
|
| 29 |
+
"<|reserved_special_token_21|>",
|
| 30 |
+
"<|reserved_special_token_22|>",
|
| 31 |
+
"<|reserved_special_token_23|>",
|
| 32 |
+
"<|reserved_special_token_24|>",
|
| 33 |
+
"<|reserved_special_token_25|>",
|
| 34 |
+
"<|reserved_special_token_26|>",
|
| 35 |
+
"<|reserved_special_token_27|>",
|
| 36 |
+
"<|reserved_special_token_28|>",
|
| 37 |
+
"<|reserved_special_token_29|>",
|
| 38 |
+
"<|reserved_special_token_30|>",
|
| 39 |
+
"<|reserved_special_token_31|>",
|
| 40 |
+
"<|reserved_special_token_32|>",
|
| 41 |
+
"<|reserved_special_token_33|>",
|
| 42 |
+
"<|reserved_special_token_34|>",
|
| 43 |
+
"<|reserved_special_token_35|>",
|
| 44 |
+
"<|reserved_special_token_36|>",
|
| 45 |
+
"<|reserved_special_token_37|>",
|
| 46 |
+
"<|reserved_special_token_38|>",
|
| 47 |
+
"<|reserved_special_token_39|>",
|
| 48 |
+
"<|reserved_special_token_40|>",
|
| 49 |
+
"<|reserved_special_token_41|>",
|
| 50 |
+
"<|reserved_special_token_42|>",
|
| 51 |
+
"<|reserved_special_token_43|>",
|
| 52 |
+
"<|reserved_special_token_44|>",
|
| 53 |
+
"<|reserved_special_token_45|>",
|
| 54 |
+
"<|reserved_special_token_46|>",
|
| 55 |
+
"<|reserved_special_token_47|>",
|
| 56 |
+
"<|reserved_special_token_48|>",
|
| 57 |
+
"<|reserved_special_token_49|>",
|
| 58 |
+
"<|reserved_special_token_50|>",
|
| 59 |
+
"<|reserved_special_token_51|>",
|
| 60 |
+
"<|reserved_special_token_52|>",
|
| 61 |
+
"<|reserved_special_token_53|>",
|
| 62 |
+
"<|reserved_special_token_54|>",
|
| 63 |
+
"<|reserved_special_token_55|>",
|
| 64 |
+
"<|reserved_special_token_56|>",
|
| 65 |
+
"<|reserved_special_token_57|>",
|
| 66 |
+
"<|reserved_special_token_58|>",
|
| 67 |
+
"<|reserved_special_token_59|>",
|
| 68 |
+
"<|reserved_special_token_60|>",
|
| 69 |
+
"<|reserved_special_token_61|>",
|
| 70 |
+
"<|reserved_special_token_62|>",
|
| 71 |
+
"<|reserved_special_token_63|>",
|
| 72 |
+
"<|reserved_special_token_64|>",
|
| 73 |
+
"<|reserved_special_token_65|>",
|
| 74 |
+
"<|reserved_special_token_66|>",
|
| 75 |
+
"<|reserved_special_token_67|>",
|
| 76 |
+
"<|reserved_special_token_68|>",
|
| 77 |
+
"<|reserved_special_token_69|>",
|
| 78 |
+
"<|reserved_special_token_70|>",
|
| 79 |
+
"<|reserved_special_token_71|>",
|
| 80 |
+
"<|reserved_special_token_72|>",
|
| 81 |
+
"<|reserved_special_token_73|>",
|
| 82 |
+
"<|reserved_special_token_74|>",
|
| 83 |
+
"<|reserved_special_token_75|>",
|
| 84 |
+
"<|reserved_special_token_76|>",
|
| 85 |
+
"<|reserved_special_token_77|>",
|
| 86 |
+
"<|reserved_special_token_78|>",
|
| 87 |
+
"<|reserved_special_token_79|>",
|
| 88 |
+
"<|reserved_special_token_80|>",
|
| 89 |
+
"<|reserved_special_token_81|>",
|
| 90 |
+
"<|reserved_special_token_82|>",
|
| 91 |
+
"<|reserved_special_token_83|>",
|
| 92 |
+
"<|reserved_special_token_84|>",
|
| 93 |
+
"<|reserved_special_token_85|>",
|
| 94 |
+
"<|reserved_special_token_86|>",
|
| 95 |
+
"<|reserved_special_token_87|>",
|
| 96 |
+
"<|reserved_special_token_88|>",
|
| 97 |
+
"<|reserved_special_token_89|>",
|
| 98 |
+
"<|reserved_special_token_90|>",
|
| 99 |
+
"<|reserved_special_token_91|>",
|
| 100 |
+
"<|reserved_special_token_92|>",
|
| 101 |
+
"<|reserved_special_token_93|>",
|
| 102 |
+
"<|reserved_special_token_94|>",
|
| 103 |
+
"<|reserved_special_token_95|>",
|
| 104 |
+
"<|reserved_special_token_96|>",
|
| 105 |
+
"<|reserved_special_token_97|>",
|
| 106 |
+
"<|reserved_special_token_98|>",
|
| 107 |
+
"<|reserved_special_token_99|>",
|
| 108 |
+
"<|reserved_special_token_100|>",
|
| 109 |
+
"<|reserved_special_token_101|>",
|
| 110 |
+
"<|reserved_special_token_102|>",
|
| 111 |
+
"<|reserved_special_token_103|>",
|
| 112 |
+
"<|reserved_special_token_104|>",
|
| 113 |
+
"<|reserved_special_token_105|>",
|
| 114 |
+
"<|reserved_special_token_106|>",
|
| 115 |
+
"<|reserved_special_token_107|>",
|
| 116 |
+
"<|reserved_special_token_108|>",
|
| 117 |
+
"<|reserved_special_token_109|>",
|
| 118 |
+
"<|reserved_special_token_110|>",
|
| 119 |
+
"<|reserved_special_token_111|>",
|
| 120 |
+
"<|reserved_special_token_112|>",
|
| 121 |
+
"<|reserved_special_token_113|>",
|
| 122 |
+
"<|reserved_special_token_114|>",
|
| 123 |
+
"<|reserved_special_token_115|>",
|
| 124 |
+
"<|reserved_special_token_116|>",
|
| 125 |
+
"<|reserved_special_token_117|>",
|
| 126 |
+
"<|reserved_special_token_118|>",
|
| 127 |
+
"<|reserved_special_token_119|>",
|
| 128 |
+
"<|reserved_special_token_120|>",
|
| 129 |
+
"<|reserved_special_token_121|>",
|
| 130 |
+
"<|reserved_special_token_122|>",
|
| 131 |
+
"<|reserved_special_token_123|>",
|
| 132 |
+
"<|reserved_special_token_124|>",
|
| 133 |
+
"<|reserved_special_token_125|>",
|
| 134 |
+
"<|reserved_special_token_126|>",
|
| 135 |
+
"<|reserved_special_token_127|>",
|
| 136 |
+
"<|reserved_special_token_128|>",
|
| 137 |
+
"<|reserved_special_token_129|>",
|
| 138 |
+
"<|reserved_special_token_130|>",
|
| 139 |
+
"<|reserved_special_token_131|>",
|
| 140 |
+
"<|reserved_special_token_132|>",
|
| 141 |
+
"<|reserved_special_token_133|>",
|
| 142 |
+
"<|reserved_special_token_134|>",
|
| 143 |
+
"<|reserved_special_token_135|>",
|
| 144 |
+
"<|reserved_special_token_136|>",
|
| 145 |
+
"<|reserved_special_token_137|>",
|
| 146 |
+
"<|reserved_special_token_138|>",
|
| 147 |
+
"<|reserved_special_token_139|>",
|
| 148 |
+
"<|reserved_special_token_140|>",
|
| 149 |
+
"<|reserved_special_token_141|>",
|
| 150 |
+
"<|reserved_special_token_142|>",
|
| 151 |
+
"<|reserved_special_token_143|>",
|
| 152 |
+
"<|reserved_special_token_144|>",
|
| 153 |
+
"<|reserved_special_token_145|>",
|
| 154 |
+
"<|reserved_special_token_146|>",
|
| 155 |
+
"<|reserved_special_token_147|>",
|
| 156 |
+
"<|reserved_special_token_148|>",
|
| 157 |
+
"<|reserved_special_token_149|>",
|
| 158 |
+
"<|reserved_special_token_150|>",
|
| 159 |
+
"<|reserved_special_token_151|>",
|
| 160 |
+
"<|reserved_special_token_152|>",
|
| 161 |
+
"<|reserved_special_token_153|>",
|
| 162 |
+
"<|reserved_special_token_154|>",
|
| 163 |
+
"<|reserved_special_token_155|>",
|
| 164 |
+
"<|reserved_special_token_156|>",
|
| 165 |
+
"<|reserved_special_token_157|>",
|
| 166 |
+
"<|reserved_special_token_158|>",
|
| 167 |
+
"<|reserved_special_token_159|>",
|
| 168 |
+
"<|reserved_special_token_160|>",
|
| 169 |
+
"<|reserved_special_token_161|>",
|
| 170 |
+
"<|reserved_special_token_162|>",
|
| 171 |
+
"<|reserved_special_token_163|>",
|
| 172 |
+
"<|reserved_special_token_164|>",
|
| 173 |
+
"<|reserved_special_token_165|>",
|
| 174 |
+
"<|reserved_special_token_166|>",
|
| 175 |
+
"<|reserved_special_token_167|>",
|
| 176 |
+
"<|reserved_special_token_168|>",
|
| 177 |
+
"<|reserved_special_token_169|>",
|
| 178 |
+
"<|reserved_special_token_170|>",
|
| 179 |
+
"<|reserved_special_token_171|>",
|
| 180 |
+
"<|reserved_special_token_172|>",
|
| 181 |
+
"<|reserved_special_token_173|>",
|
| 182 |
+
"<|reserved_special_token_174|>",
|
| 183 |
+
"<|reserved_special_token_175|>",
|
| 184 |
+
"<|reserved_special_token_176|>",
|
| 185 |
+
"<|reserved_special_token_177|>",
|
| 186 |
+
"<|reserved_special_token_178|>",
|
| 187 |
+
"<|reserved_special_token_179|>",
|
| 188 |
+
"<|reserved_special_token_180|>",
|
| 189 |
+
"<|reserved_special_token_181|>",
|
| 190 |
+
"<|reserved_special_token_182|>",
|
| 191 |
+
"<|reserved_special_token_183|>",
|
| 192 |
+
"<|reserved_special_token_184|>",
|
| 193 |
+
"<|reserved_special_token_185|>",
|
| 194 |
+
"<|reserved_special_token_186|>",
|
| 195 |
+
"<|reserved_special_token_187|>",
|
| 196 |
+
"<|reserved_special_token_188|>",
|
| 197 |
+
"<|reserved_special_token_189|>",
|
| 198 |
+
"<|reserved_special_token_190|>",
|
| 199 |
+
"<|reserved_special_token_191|>",
|
| 200 |
+
"<|reserved_special_token_192|>",
|
| 201 |
+
"<|reserved_special_token_193|>",
|
| 202 |
+
"<|reserved_special_token_194|>",
|
| 203 |
+
"<|reserved_special_token_195|>",
|
| 204 |
+
"<|reserved_special_token_196|>",
|
| 205 |
+
"<|reserved_special_token_197|>",
|
| 206 |
+
"<|reserved_special_token_198|>",
|
| 207 |
+
"<|reserved_special_token_199|>",
|
| 208 |
+
"<|reserved_special_token_200|>",
|
| 209 |
+
"<|reserved_special_token_201|>",
|
| 210 |
+
"<|reserved_special_token_202|>",
|
| 211 |
+
"<|reserved_special_token_203|>",
|
| 212 |
+
"<|reserved_special_token_204|>",
|
| 213 |
+
"<|reserved_special_token_205|>",
|
| 214 |
+
"<|reserved_special_token_206|>",
|
| 215 |
+
"<|reserved_special_token_207|>",
|
| 216 |
+
"<|reserved_special_token_208|>",
|
| 217 |
+
"<|reserved_special_token_209|>",
|
| 218 |
+
"<|reserved_special_token_210|>",
|
| 219 |
+
"<|reserved_special_token_211|>",
|
| 220 |
+
"<|reserved_special_token_212|>",
|
| 221 |
+
"<|reserved_special_token_213|>",
|
| 222 |
+
"<|reserved_special_token_214|>",
|
| 223 |
+
"<|reserved_special_token_215|>",
|
| 224 |
+
"<|reserved_special_token_216|>",
|
| 225 |
+
"<|reserved_special_token_217|>",
|
| 226 |
+
"<|reserved_special_token_218|>",
|
| 227 |
+
"<|reserved_special_token_219|>",
|
| 228 |
+
"<|reserved_special_token_220|>",
|
| 229 |
+
"<|reserved_special_token_221|>",
|
| 230 |
+
"<|reserved_special_token_222|>",
|
| 231 |
+
"<|reserved_special_token_223|>",
|
| 232 |
+
"<|reserved_special_token_224|>",
|
| 233 |
+
"<|reserved_special_token_225|>",
|
| 234 |
+
"<|reserved_special_token_226|>",
|
| 235 |
+
"<|reserved_special_token_227|>",
|
| 236 |
+
"<|reserved_special_token_228|>",
|
| 237 |
+
"<|reserved_special_token_229|>",
|
| 238 |
+
"<|reserved_special_token_230|>",
|
| 239 |
+
"<|reserved_special_token_231|>",
|
| 240 |
+
"<|reserved_special_token_232|>",
|
| 241 |
+
"<|reserved_special_token_233|>",
|
| 242 |
+
"<|reserved_special_token_234|>",
|
| 243 |
+
"<|reserved_special_token_235|>",
|
| 244 |
+
"<|reserved_special_token_236|>",
|
| 245 |
+
"<|reserved_special_token_237|>",
|
| 246 |
+
"<|reserved_special_token_238|>",
|
| 247 |
+
"<|reserved_special_token_239|>",
|
| 248 |
+
"<|reserved_special_token_240|>",
|
| 249 |
+
"<|reserved_special_token_241|>",
|
| 250 |
+
"<|reserved_special_token_242|>",
|
| 251 |
+
"<|reserved_special_token_243|>",
|
| 252 |
+
"<|reserved_special_token_244|>",
|
| 253 |
+
"<|reserved_special_token_245|>",
|
| 254 |
+
"<|reserved_special_token_246|>",
|
| 255 |
+
"<|reserved_special_token_247|>",
|
| 256 |
+
"<|reserved_special_token_248|>",
|
| 257 |
+
"<|reserved_special_token_249|>",
|
| 258 |
+
"<|reserved_special_token_250|>"
|
| 259 |
+
],
|
| 260 |
+
"bos_token": {
|
| 261 |
+
"content": "<|begin_of_text|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false
|
| 266 |
+
},
|
| 267 |
+
"eos_token": {
|
| 268 |
+
"content": "<|end_of_text|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false
|
| 273 |
+
},
|
| 274 |
+
"pad_token": {
|
| 275 |
+
"content": "|<PAD>|",
|
| 276 |
+
"lstrip": false,
|
| 277 |
+
"normalized": false,
|
| 278 |
+
"rstrip": false,
|
| 279 |
+
"single_word": false
|
| 280 |
+
},
|
| 281 |
+
"sep_token": {
|
| 282 |
+
"content": "|<SEP>|",
|
| 283 |
+
"lstrip": false,
|
| 284 |
+
"normalized": false,
|
| 285 |
+
"rstrip": false,
|
| 286 |
+
"single_word": false
|
| 287 |
+
}
|
| 288 |
+
}
|