Commit 
							
							·
						
						0f66715
	
1
								Parent(s):
							
							55af551
								
Remove added tokens to make compatible with tokenizers>=0.14 (#1)
Browse files- Add change (8a0a1f64dbdd411b93489813a4b684fc6452c658)
- Update tokenizer_config.json (ec0cf7f2919e4d9d3f79198cf0472d5cd3521f1d)
Co-authored-by: VConm <[email protected]>
- tokenizer.json +0 -207
    	
        tokenizer.json
    CHANGED
    
    | @@ -29,213 +29,6 @@ | |
| 29 | 
             
                  "rstrip": false,
         | 
| 30 | 
             
                  "normalized": false,
         | 
| 31 | 
             
                  "special": true
         | 
| 32 | 
            -
                },
         | 
| 33 | 
            -
                {
         | 
| 34 | 
            -
                  "id": 48239,
         | 
| 35 | 
            -
                  "content": "                        ",
         | 
| 36 | 
            -
                  "single_word": false,
         | 
| 37 | 
            -
                  "lstrip": false,
         | 
| 38 | 
            -
                  "rstrip": false,
         | 
| 39 | 
            -
                  "normalized": true,
         | 
| 40 | 
            -
                  "special": false
         | 
| 41 | 
            -
                },
         | 
| 42 | 
            -
                {
         | 
| 43 | 
            -
                  "id": 48240,
         | 
| 44 | 
            -
                  "content": "                       ",
         | 
| 45 | 
            -
                  "single_word": false,
         | 
| 46 | 
            -
                  "lstrip": false,
         | 
| 47 | 
            -
                  "rstrip": false,
         | 
| 48 | 
            -
                  "normalized": true,
         | 
| 49 | 
            -
                  "special": false
         | 
| 50 | 
            -
                },
         | 
| 51 | 
            -
                {
         | 
| 52 | 
            -
                  "id": 48241,
         | 
| 53 | 
            -
                  "content": "                      ",
         | 
| 54 | 
            -
                  "single_word": false,
         | 
| 55 | 
            -
                  "lstrip": false,
         | 
| 56 | 
            -
                  "rstrip": false,
         | 
| 57 | 
            -
                  "normalized": true,
         | 
| 58 | 
            -
                  "special": false
         | 
| 59 | 
            -
                },
         | 
| 60 | 
            -
                {
         | 
| 61 | 
            -
                  "id": 48242,
         | 
| 62 | 
            -
                  "content": "                     ",
         | 
| 63 | 
            -
                  "single_word": false,
         | 
| 64 | 
            -
                  "lstrip": false,
         | 
| 65 | 
            -
                  "rstrip": false,
         | 
| 66 | 
            -
                  "normalized": true,
         | 
| 67 | 
            -
                  "special": false
         | 
| 68 | 
            -
                },
         | 
| 69 | 
            -
                {
         | 
| 70 | 
            -
                  "id": 48243,
         | 
| 71 | 
            -
                  "content": "                    ",
         | 
| 72 | 
            -
                  "single_word": false,
         | 
| 73 | 
            -
                  "lstrip": false,
         | 
| 74 | 
            -
                  "rstrip": false,
         | 
| 75 | 
            -
                  "normalized": true,
         | 
| 76 | 
            -
                  "special": false
         | 
| 77 | 
            -
                },
         | 
| 78 | 
            -
                {
         | 
| 79 | 
            -
                  "id": 48244,
         | 
| 80 | 
            -
                  "content": "                   ",
         | 
| 81 | 
            -
                  "single_word": false,
         | 
| 82 | 
            -
                  "lstrip": false,
         | 
| 83 | 
            -
                  "rstrip": false,
         | 
| 84 | 
            -
                  "normalized": true,
         | 
| 85 | 
            -
                  "special": false
         | 
| 86 | 
            -
                },
         | 
| 87 | 
            -
                {
         | 
| 88 | 
            -
                  "id": 48245,
         | 
| 89 | 
            -
                  "content": "                  ",
         | 
| 90 | 
            -
                  "single_word": false,
         | 
| 91 | 
            -
                  "lstrip": false,
         | 
| 92 | 
            -
                  "rstrip": false,
         | 
| 93 | 
            -
                  "normalized": true,
         | 
| 94 | 
            -
                  "special": false
         | 
| 95 | 
            -
                },
         | 
| 96 | 
            -
                {
         | 
| 97 | 
            -
                  "id": 48246,
         | 
| 98 | 
            -
                  "content": "                 ",
         | 
| 99 | 
            -
                  "single_word": false,
         | 
| 100 | 
            -
                  "lstrip": false,
         | 
| 101 | 
            -
                  "rstrip": false,
         | 
| 102 | 
            -
                  "normalized": true,
         | 
| 103 | 
            -
                  "special": false
         | 
| 104 | 
            -
                },
         | 
| 105 | 
            -
                {
         | 
| 106 | 
            -
                  "id": 48247,
         | 
| 107 | 
            -
                  "content": "                ",
         | 
| 108 | 
            -
                  "single_word": false,
         | 
| 109 | 
            -
                  "lstrip": false,
         | 
| 110 | 
            -
                  "rstrip": false,
         | 
| 111 | 
            -
                  "normalized": true,
         | 
| 112 | 
            -
                  "special": false
         | 
| 113 | 
            -
                },
         | 
| 114 | 
            -
                {
         | 
| 115 | 
            -
                  "id": 48248,
         | 
| 116 | 
            -
                  "content": "               ",
         | 
| 117 | 
            -
                  "single_word": false,
         | 
| 118 | 
            -
                  "lstrip": false,
         | 
| 119 | 
            -
                  "rstrip": false,
         | 
| 120 | 
            -
                  "normalized": true,
         | 
| 121 | 
            -
                  "special": false
         | 
| 122 | 
            -
                },
         | 
| 123 | 
            -
                {
         | 
| 124 | 
            -
                  "id": 48249,
         | 
| 125 | 
            -
                  "content": "              ",
         | 
| 126 | 
            -
                  "single_word": false,
         | 
| 127 | 
            -
                  "lstrip": false,
         | 
| 128 | 
            -
                  "rstrip": false,
         | 
| 129 | 
            -
                  "normalized": true,
         | 
| 130 | 
            -
                  "special": false
         | 
| 131 | 
            -
                },
         | 
| 132 | 
            -
                {
         | 
| 133 | 
            -
                  "id": 48250,
         | 
| 134 | 
            -
                  "content": "             ",
         | 
| 135 | 
            -
                  "single_word": false,
         | 
| 136 | 
            -
                  "lstrip": false,
         | 
| 137 | 
            -
                  "rstrip": false,
         | 
| 138 | 
            -
                  "normalized": true,
         | 
| 139 | 
            -
                  "special": false
         | 
| 140 | 
            -
                },
         | 
| 141 | 
            -
                {
         | 
| 142 | 
            -
                  "id": 48251,
         | 
| 143 | 
            -
                  "content": "            ",
         | 
| 144 | 
            -
                  "single_word": false,
         | 
| 145 | 
            -
                  "lstrip": false,
         | 
| 146 | 
            -
                  "rstrip": false,
         | 
| 147 | 
            -
                  "normalized": true,
         | 
| 148 | 
            -
                  "special": false
         | 
| 149 | 
            -
                },
         | 
| 150 | 
            -
                {
         | 
| 151 | 
            -
                  "id": 48252,
         | 
| 152 | 
            -
                  "content": "           ",
         | 
| 153 | 
            -
                  "single_word": false,
         | 
| 154 | 
            -
                  "lstrip": false,
         | 
| 155 | 
            -
                  "rstrip": false,
         | 
| 156 | 
            -
                  "normalized": true,
         | 
| 157 | 
            -
                  "special": false
         | 
| 158 | 
            -
                },
         | 
| 159 | 
            -
                {
         | 
| 160 | 
            -
                  "id": 48253,
         | 
| 161 | 
            -
                  "content": "          ",
         | 
| 162 | 
            -
                  "single_word": false,
         | 
| 163 | 
            -
                  "lstrip": false,
         | 
| 164 | 
            -
                  "rstrip": false,
         | 
| 165 | 
            -
                  "normalized": true,
         | 
| 166 | 
            -
                  "special": false
         | 
| 167 | 
            -
                },
         | 
| 168 | 
            -
                {
         | 
| 169 | 
            -
                  "id": 48254,
         | 
| 170 | 
            -
                  "content": "         ",
         | 
| 171 | 
            -
                  "single_word": false,
         | 
| 172 | 
            -
                  "lstrip": false,
         | 
| 173 | 
            -
                  "rstrip": false,
         | 
| 174 | 
            -
                  "normalized": true,
         | 
| 175 | 
            -
                  "special": false
         | 
| 176 | 
            -
                },
         | 
| 177 | 
            -
                {
         | 
| 178 | 
            -
                  "id": 48255,
         | 
| 179 | 
            -
                  "content": "        ",
         | 
| 180 | 
            -
                  "single_word": false,
         | 
| 181 | 
            -
                  "lstrip": false,
         | 
| 182 | 
            -
                  "rstrip": false,
         | 
| 183 | 
            -
                  "normalized": true,
         | 
| 184 | 
            -
                  "special": false
         | 
| 185 | 
            -
                },
         | 
| 186 | 
            -
                {
         | 
| 187 | 
            -
                  "id": 48256,
         | 
| 188 | 
            -
                  "content": "       ",
         | 
| 189 | 
            -
                  "single_word": false,
         | 
| 190 | 
            -
                  "lstrip": false,
         | 
| 191 | 
            -
                  "rstrip": false,
         | 
| 192 | 
            -
                  "normalized": true,
         | 
| 193 | 
            -
                  "special": false
         | 
| 194 | 
            -
                },
         | 
| 195 | 
            -
                {
         | 
| 196 | 
            -
                  "id": 48257,
         | 
| 197 | 
            -
                  "content": "      ",
         | 
| 198 | 
            -
                  "single_word": false,
         | 
| 199 | 
            -
                  "lstrip": false,
         | 
| 200 | 
            -
                  "rstrip": false,
         | 
| 201 | 
            -
                  "normalized": true,
         | 
| 202 | 
            -
                  "special": false
         | 
| 203 | 
            -
                },
         | 
| 204 | 
            -
                {
         | 
| 205 | 
            -
                  "id": 48258,
         | 
| 206 | 
            -
                  "content": "     ",
         | 
| 207 | 
            -
                  "single_word": false,
         | 
| 208 | 
            -
                  "lstrip": false,
         | 
| 209 | 
            -
                  "rstrip": false,
         | 
| 210 | 
            -
                  "normalized": true,
         | 
| 211 | 
            -
                  "special": false
         | 
| 212 | 
            -
                },
         | 
| 213 | 
            -
                {
         | 
| 214 | 
            -
                  "id": 48259,
         | 
| 215 | 
            -
                  "content": "    ",
         | 
| 216 | 
            -
                  "single_word": false,
         | 
| 217 | 
            -
                  "lstrip": false,
         | 
| 218 | 
            -
                  "rstrip": false,
         | 
| 219 | 
            -
                  "normalized": true,
         | 
| 220 | 
            -
                  "special": false
         | 
| 221 | 
            -
                },
         | 
| 222 | 
            -
                {
         | 
| 223 | 
            -
                  "id": 48260,
         | 
| 224 | 
            -
                  "content": "   ",
         | 
| 225 | 
            -
                  "single_word": false,
         | 
| 226 | 
            -
                  "lstrip": false,
         | 
| 227 | 
            -
                  "rstrip": false,
         | 
| 228 | 
            -
                  "normalized": true,
         | 
| 229 | 
            -
                  "special": false
         | 
| 230 | 
            -
                },
         | 
| 231 | 
            -
                {
         | 
| 232 | 
            -
                  "id": 48261,
         | 
| 233 | 
            -
                  "content": "  ",
         | 
| 234 | 
            -
                  "single_word": false,
         | 
| 235 | 
            -
                  "lstrip": false,
         | 
| 236 | 
            -
                  "rstrip": false,
         | 
| 237 | 
            -
                  "normalized": true,
         | 
| 238 | 
            -
                  "special": false
         | 
| 239 | 
             
                }
         | 
| 240 | 
             
              ],
         | 
| 241 | 
             
              "normalizer": {
         | 
|  | |
| 29 | 
             
                  "rstrip": false,
         | 
| 30 | 
             
                  "normalized": false,
         | 
| 31 | 
             
                  "special": true
         | 
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
| 32 | 
             
                }
         | 
| 33 | 
             
              ],
         | 
| 34 | 
             
              "normalizer": {
         |