Upload 6 files
Browse files- added_tokens.json +201 -0
- merges.txt +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<endoftext>": 50454,
|
| 3 |
+
"<|extratoken_100|>": 50356,
|
| 4 |
+
"<|extratoken_101|>": 50357,
|
| 5 |
+
"<|extratoken_102|>": 50358,
|
| 6 |
+
"<|extratoken_103|>": 50359,
|
| 7 |
+
"<|extratoken_104|>": 50360,
|
| 8 |
+
"<|extratoken_105|>": 50361,
|
| 9 |
+
"<|extratoken_106|>": 50362,
|
| 10 |
+
"<|extratoken_107|>": 50363,
|
| 11 |
+
"<|extratoken_108|>": 50364,
|
| 12 |
+
"<|extratoken_109|>": 50365,
|
| 13 |
+
"<|extratoken_10|>": 50266,
|
| 14 |
+
"<|extratoken_110|>": 50366,
|
| 15 |
+
"<|extratoken_111|>": 50367,
|
| 16 |
+
"<|extratoken_112|>": 50368,
|
| 17 |
+
"<|extratoken_113|>": 50369,
|
| 18 |
+
"<|extratoken_114|>": 50370,
|
| 19 |
+
"<|extratoken_115|>": 50371,
|
| 20 |
+
"<|extratoken_116|>": 50372,
|
| 21 |
+
"<|extratoken_117|>": 50373,
|
| 22 |
+
"<|extratoken_118|>": 50374,
|
| 23 |
+
"<|extratoken_119|>": 50375,
|
| 24 |
+
"<|extratoken_11|>": 50267,
|
| 25 |
+
"<|extratoken_120|>": 50376,
|
| 26 |
+
"<|extratoken_121|>": 50377,
|
| 27 |
+
"<|extratoken_122|>": 50378,
|
| 28 |
+
"<|extratoken_123|>": 50379,
|
| 29 |
+
"<|extratoken_124|>": 50380,
|
| 30 |
+
"<|extratoken_125|>": 50381,
|
| 31 |
+
"<|extratoken_126|>": 50382,
|
| 32 |
+
"<|extratoken_127|>": 50383,
|
| 33 |
+
"<|extratoken_128|>": 50384,
|
| 34 |
+
"<|extratoken_129|>": 50385,
|
| 35 |
+
"<|extratoken_12|>": 50268,
|
| 36 |
+
"<|extratoken_130|>": 50386,
|
| 37 |
+
"<|extratoken_131|>": 50387,
|
| 38 |
+
"<|extratoken_132|>": 50388,
|
| 39 |
+
"<|extratoken_133|>": 50389,
|
| 40 |
+
"<|extratoken_134|>": 50390,
|
| 41 |
+
"<|extratoken_135|>": 50391,
|
| 42 |
+
"<|extratoken_136|>": 50392,
|
| 43 |
+
"<|extratoken_137|>": 50393,
|
| 44 |
+
"<|extratoken_138|>": 50394,
|
| 45 |
+
"<|extratoken_139|>": 50395,
|
| 46 |
+
"<|extratoken_13|>": 50269,
|
| 47 |
+
"<|extratoken_140|>": 50396,
|
| 48 |
+
"<|extratoken_141|>": 50397,
|
| 49 |
+
"<|extratoken_142|>": 50398,
|
| 50 |
+
"<|extratoken_143|>": 50399,
|
| 51 |
+
"<|extratoken_14|>": 50270,
|
| 52 |
+
"<|extratoken_15|>": 50271,
|
| 53 |
+
"<|extratoken_16|>": 50272,
|
| 54 |
+
"<|extratoken_17|>": 50273,
|
| 55 |
+
"<|extratoken_18|>": 50274,
|
| 56 |
+
"<|extratoken_19|>": 50275,
|
| 57 |
+
"<|extratoken_1|>": 50257,
|
| 58 |
+
"<|extratoken_20|>": 50276,
|
| 59 |
+
"<|extratoken_21|>": 50277,
|
| 60 |
+
"<|extratoken_22|>": 50278,
|
| 61 |
+
"<|extratoken_23|>": 50279,
|
| 62 |
+
"<|extratoken_24|>": 50280,
|
| 63 |
+
"<|extratoken_25|>": 50281,
|
| 64 |
+
"<|extratoken_26|>": 50282,
|
| 65 |
+
"<|extratoken_27|>": 50283,
|
| 66 |
+
"<|extratoken_28|>": 50284,
|
| 67 |
+
"<|extratoken_29|>": 50285,
|
| 68 |
+
"<|extratoken_2|>": 50258,
|
| 69 |
+
"<|extratoken_30|>": 50286,
|
| 70 |
+
"<|extratoken_31|>": 50287,
|
| 71 |
+
"<|extratoken_32|>": 50288,
|
| 72 |
+
"<|extratoken_33|>": 50289,
|
| 73 |
+
"<|extratoken_34|>": 50290,
|
| 74 |
+
"<|extratoken_35|>": 50291,
|
| 75 |
+
"<|extratoken_36|>": 50292,
|
| 76 |
+
"<|extratoken_37|>": 50293,
|
| 77 |
+
"<|extratoken_38|>": 50294,
|
| 78 |
+
"<|extratoken_39|>": 50295,
|
| 79 |
+
"<|extratoken_3|>": 50259,
|
| 80 |
+
"<|extratoken_40|>": 50296,
|
| 81 |
+
"<|extratoken_41|>": 50297,
|
| 82 |
+
"<|extratoken_42|>": 50298,
|
| 83 |
+
"<|extratoken_43|>": 50299,
|
| 84 |
+
"<|extratoken_44|>": 50300,
|
| 85 |
+
"<|extratoken_45|>": 50301,
|
| 86 |
+
"<|extratoken_46|>": 50302,
|
| 87 |
+
"<|extratoken_47|>": 50303,
|
| 88 |
+
"<|extratoken_48|>": 50304,
|
| 89 |
+
"<|extratoken_49|>": 50305,
|
| 90 |
+
"<|extratoken_4|>": 50260,
|
| 91 |
+
"<|extratoken_50|>": 50306,
|
| 92 |
+
"<|extratoken_51|>": 50307,
|
| 93 |
+
"<|extratoken_52|>": 50308,
|
| 94 |
+
"<|extratoken_53|>": 50309,
|
| 95 |
+
"<|extratoken_54|>": 50310,
|
| 96 |
+
"<|extratoken_55|>": 50311,
|
| 97 |
+
"<|extratoken_56|>": 50312,
|
| 98 |
+
"<|extratoken_57|>": 50313,
|
| 99 |
+
"<|extratoken_58|>": 50314,
|
| 100 |
+
"<|extratoken_59|>": 50315,
|
| 101 |
+
"<|extratoken_5|>": 50261,
|
| 102 |
+
"<|extratoken_60|>": 50316,
|
| 103 |
+
"<|extratoken_61|>": 50317,
|
| 104 |
+
"<|extratoken_62|>": 50318,
|
| 105 |
+
"<|extratoken_63|>": 50319,
|
| 106 |
+
"<|extratoken_64|>": 50320,
|
| 107 |
+
"<|extratoken_65|>": 50321,
|
| 108 |
+
"<|extratoken_66|>": 50322,
|
| 109 |
+
"<|extratoken_67|>": 50323,
|
| 110 |
+
"<|extratoken_68|>": 50324,
|
| 111 |
+
"<|extratoken_69|>": 50325,
|
| 112 |
+
"<|extratoken_6|>": 50262,
|
| 113 |
+
"<|extratoken_70|>": 50326,
|
| 114 |
+
"<|extratoken_71|>": 50327,
|
| 115 |
+
"<|extratoken_72|>": 50328,
|
| 116 |
+
"<|extratoken_73|>": 50329,
|
| 117 |
+
"<|extratoken_74|>": 50330,
|
| 118 |
+
"<|extratoken_75|>": 50331,
|
| 119 |
+
"<|extratoken_76|>": 50332,
|
| 120 |
+
"<|extratoken_77|>": 50333,
|
| 121 |
+
"<|extratoken_78|>": 50334,
|
| 122 |
+
"<|extratoken_79|>": 50335,
|
| 123 |
+
"<|extratoken_7|>": 50263,
|
| 124 |
+
"<|extratoken_80|>": 50336,
|
| 125 |
+
"<|extratoken_81|>": 50337,
|
| 126 |
+
"<|extratoken_82|>": 50338,
|
| 127 |
+
"<|extratoken_83|>": 50339,
|
| 128 |
+
"<|extratoken_84|>": 50340,
|
| 129 |
+
"<|extratoken_85|>": 50341,
|
| 130 |
+
"<|extratoken_86|>": 50342,
|
| 131 |
+
"<|extratoken_87|>": 50343,
|
| 132 |
+
"<|extratoken_88|>": 50344,
|
| 133 |
+
"<|extratoken_89|>": 50345,
|
| 134 |
+
"<|extratoken_8|>": 50264,
|
| 135 |
+
"<|extratoken_90|>": 50346,
|
| 136 |
+
"<|extratoken_91|>": 50347,
|
| 137 |
+
"<|extratoken_92|>": 50348,
|
| 138 |
+
"<|extratoken_93|>": 50349,
|
| 139 |
+
"<|extratoken_94|>": 50350,
|
| 140 |
+
"<|extratoken_95|>": 50351,
|
| 141 |
+
"<|extratoken_96|>": 50352,
|
| 142 |
+
"<|extratoken_97|>": 50353,
|
| 143 |
+
"<|extratoken_98|>": 50354,
|
| 144 |
+
"<|extratoken_99|>": 50355,
|
| 145 |
+
"<|extratoken_9|>": 50265,
|
| 146 |
+
"[/LCM]": 50427,
|
| 147 |
+
"[/add]": 50431,
|
| 148 |
+
"[/compare]": 50446,
|
| 149 |
+
"[/convert]": 50444,
|
| 150 |
+
"[/div]": 50432,
|
| 151 |
+
"[/divide]": 50442,
|
| 152 |
+
"[/find]": 50435,
|
| 153 |
+
"[/find_gcd]": 50452,
|
| 154 |
+
"[/find_lcm]": 50448,
|
| 155 |
+
"[/floor]": 50437,
|
| 156 |
+
"[/gcd]": 50428,
|
| 157 |
+
"[/lcm]": 50434,
|
| 158 |
+
"[/mod]": 50430,
|
| 159 |
+
"[/modulo]": 50440,
|
| 160 |
+
"[/mul]": 50429,
|
| 161 |
+
"[/mult]": 50436,
|
| 162 |
+
"[/multiply]": 50447,
|
| 163 |
+
"[/power]": 50439,
|
| 164 |
+
"[/raise_to]": 50450,
|
| 165 |
+
"[/return]": 50441,
|
| 166 |
+
"[/reverse]": 50443,
|
| 167 |
+
"[/round]": 50438,
|
| 168 |
+
"[/round_down]": 50453,
|
| 169 |
+
"[/round_up]": 50449,
|
| 170 |
+
"[/sub]": 50433,
|
| 171 |
+
"[/subtact]": 50445,
|
| 172 |
+
"[/subtract]": 50451,
|
| 173 |
+
"[CALL]": 50455,
|
| 174 |
+
"[LCM]": 50400,
|
| 175 |
+
"[add]": 50404,
|
| 176 |
+
"[compare]": 50419,
|
| 177 |
+
"[convert]": 50417,
|
| 178 |
+
"[div]": 50405,
|
| 179 |
+
"[divide]": 50415,
|
| 180 |
+
"[find]": 50408,
|
| 181 |
+
"[find_gcd]": 50425,
|
| 182 |
+
"[find_lcm]": 50421,
|
| 183 |
+
"[floor]": 50410,
|
| 184 |
+
"[gcd]": 50401,
|
| 185 |
+
"[lcm]": 50407,
|
| 186 |
+
"[mod]": 50403,
|
| 187 |
+
"[modulo]": 50413,
|
| 188 |
+
"[mul]": 50402,
|
| 189 |
+
"[mult]": 50409,
|
| 190 |
+
"[multiply]": 50420,
|
| 191 |
+
"[power]": 50412,
|
| 192 |
+
"[raise_to]": 50423,
|
| 193 |
+
"[return]": 50414,
|
| 194 |
+
"[reverse]": 50416,
|
| 195 |
+
"[round]": 50411,
|
| 196 |
+
"[round_down]": 50426,
|
| 197 |
+
"[round_up]": 50422,
|
| 198 |
+
"[sub]": 50406,
|
| 199 |
+
"[subtact]": 50418,
|
| 200 |
+
"[subtract]": 50424
|
| 201 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 2048,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|