Commit
•
b1d878d
1
Parent(s):
4a468c4
Upload tokenizer
Browse files- special_tokens_map.json +10 -4
- tokenizer.json +0 -0
- tokenizer_config.json +8 -273
special_tokens_map.json
CHANGED
|
@@ -18,22 +18,28 @@
|
|
| 18 |
"bos_token": {
|
| 19 |
"content": "<s>",
|
| 20 |
"lstrip": false,
|
| 21 |
-
"normalized":
|
| 22 |
"rstrip": false,
|
| 23 |
"single_word": false
|
| 24 |
},
|
| 25 |
"eos_token": {
|
| 26 |
"content": "</s>",
|
| 27 |
"lstrip": false,
|
| 28 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
},
|
| 32 |
-
"pad_token": "</s>",
|
| 33 |
"unk_token": {
|
| 34 |
"content": "<unk>",
|
| 35 |
"lstrip": false,
|
| 36 |
-
"normalized":
|
| 37 |
"rstrip": false,
|
| 38 |
"single_word": false
|
| 39 |
}
|
|
|
|
| 18 |
"bos_token": {
|
| 19 |
"content": "<s>",
|
| 20 |
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
"rstrip": false,
|
| 23 |
"single_word": false
|
| 24 |
},
|
| 25 |
"eos_token": {
|
| 26 |
"content": "</s>",
|
| 27 |
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"pad_token": {
|
| 33 |
+
"content": "<unk>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
| 38 |
},
|
|
|
|
| 39 |
"unk_token": {
|
| 40 |
"content": "<unk>",
|
| 41 |
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
"rstrip": false,
|
| 44 |
"single_word": false
|
| 45 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,12 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
| 8 |
"lstrip": false,
|
| 9 |
-
"normalized":
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
|
@@ -14,7 +13,7 @@
|
|
| 14 |
"1": {
|
| 15 |
"content": "<s>",
|
| 16 |
"lstrip": false,
|
| 17 |
-
"normalized":
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
|
@@ -22,276 +21,12 @@
|
|
| 22 |
"2": {
|
| 23 |
"content": "</s>",
|
| 24 |
"lstrip": false,
|
| 25 |
-
"normalized":
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
},
|
| 30 |
-
"
|
| 31 |
-
"content": "<|future_token_32|>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": true,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": false
|
| 37 |
-
},
|
| 38 |
-
"60224": {
|
| 39 |
-
"content": "<|future_token_33|>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": true,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": false
|
| 45 |
-
},
|
| 46 |
-
"60225": {
|
| 47 |
-
"content": "<|future_token_34|>",
|
| 48 |
-
"lstrip": false,
|
| 49 |
-
"normalized": true,
|
| 50 |
-
"rstrip": false,
|
| 51 |
-
"single_word": false,
|
| 52 |
-
"special": false
|
| 53 |
-
},
|
| 54 |
-
"60226": {
|
| 55 |
-
"content": "<|future_token_35|>",
|
| 56 |
-
"lstrip": false,
|
| 57 |
-
"normalized": true,
|
| 58 |
-
"rstrip": false,
|
| 59 |
-
"single_word": false,
|
| 60 |
-
"special": false
|
| 61 |
-
},
|
| 62 |
-
"60227": {
|
| 63 |
-
"content": "<|future_token_36|>",
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"normalized": true,
|
| 66 |
-
"rstrip": false,
|
| 67 |
-
"single_word": false,
|
| 68 |
-
"special": false
|
| 69 |
-
},
|
| 70 |
-
"60228": {
|
| 71 |
-
"content": "<|future_token_37|>",
|
| 72 |
-
"lstrip": false,
|
| 73 |
-
"normalized": true,
|
| 74 |
-
"rstrip": false,
|
| 75 |
-
"single_word": false,
|
| 76 |
-
"special": false
|
| 77 |
-
},
|
| 78 |
-
"60229": {
|
| 79 |
-
"content": "<|future_token_38|>",
|
| 80 |
-
"lstrip": false,
|
| 81 |
-
"normalized": true,
|
| 82 |
-
"rstrip": false,
|
| 83 |
-
"single_word": false,
|
| 84 |
-
"special": false
|
| 85 |
-
},
|
| 86 |
-
"60230": {
|
| 87 |
-
"content": "<|future_token_39|>",
|
| 88 |
-
"lstrip": false,
|
| 89 |
-
"normalized": true,
|
| 90 |
-
"rstrip": false,
|
| 91 |
-
"single_word": false,
|
| 92 |
-
"special": false
|
| 93 |
-
},
|
| 94 |
-
"60231": {
|
| 95 |
-
"content": "<|future_token_40|>",
|
| 96 |
-
"lstrip": false,
|
| 97 |
-
"normalized": true,
|
| 98 |
-
"rstrip": false,
|
| 99 |
-
"single_word": false,
|
| 100 |
-
"special": false
|
| 101 |
-
},
|
| 102 |
-
"60232": {
|
| 103 |
-
"content": "<|future_token_41|>",
|
| 104 |
-
"lstrip": false,
|
| 105 |
-
"normalized": true,
|
| 106 |
-
"rstrip": false,
|
| 107 |
-
"single_word": false,
|
| 108 |
-
"special": false
|
| 109 |
-
},
|
| 110 |
-
"60233": {
|
| 111 |
-
"content": "<|future_token_42|>",
|
| 112 |
-
"lstrip": false,
|
| 113 |
-
"normalized": true,
|
| 114 |
-
"rstrip": false,
|
| 115 |
-
"single_word": false,
|
| 116 |
-
"special": false
|
| 117 |
-
},
|
| 118 |
-
"60234": {
|
| 119 |
-
"content": "<|future_token_43|>",
|
| 120 |
-
"lstrip": false,
|
| 121 |
-
"normalized": true,
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false,
|
| 124 |
-
"special": false
|
| 125 |
-
},
|
| 126 |
-
"60235": {
|
| 127 |
-
"content": "<|future_token_44|>",
|
| 128 |
-
"lstrip": false,
|
| 129 |
-
"normalized": true,
|
| 130 |
-
"rstrip": false,
|
| 131 |
-
"single_word": false,
|
| 132 |
-
"special": false
|
| 133 |
-
},
|
| 134 |
-
"60236": {
|
| 135 |
-
"content": "<|future_token_45|>",
|
| 136 |
-
"lstrip": false,
|
| 137 |
-
"normalized": true,
|
| 138 |
-
"rstrip": false,
|
| 139 |
-
"single_word": false,
|
| 140 |
-
"special": false
|
| 141 |
-
},
|
| 142 |
-
"60237": {
|
| 143 |
-
"content": "<|future_token_46|>",
|
| 144 |
-
"lstrip": false,
|
| 145 |
-
"normalized": true,
|
| 146 |
-
"rstrip": false,
|
| 147 |
-
"single_word": false,
|
| 148 |
-
"special": false
|
| 149 |
-
},
|
| 150 |
-
"60238": {
|
| 151 |
-
"content": "<|future_token_47|>",
|
| 152 |
-
"lstrip": false,
|
| 153 |
-
"normalized": true,
|
| 154 |
-
"rstrip": false,
|
| 155 |
-
"single_word": false,
|
| 156 |
-
"special": false
|
| 157 |
-
},
|
| 158 |
-
"60239": {
|
| 159 |
-
"content": "<|future_token_48|>",
|
| 160 |
-
"lstrip": false,
|
| 161 |
-
"normalized": true,
|
| 162 |
-
"rstrip": false,
|
| 163 |
-
"single_word": false,
|
| 164 |
-
"special": false
|
| 165 |
-
},
|
| 166 |
-
"60240": {
|
| 167 |
-
"content": "<|future_token_49|>",
|
| 168 |
-
"lstrip": false,
|
| 169 |
-
"normalized": true,
|
| 170 |
-
"rstrip": false,
|
| 171 |
-
"single_word": false,
|
| 172 |
-
"special": false
|
| 173 |
-
},
|
| 174 |
-
"60241": {
|
| 175 |
-
"content": "<|future_token_50|>",
|
| 176 |
-
"lstrip": false,
|
| 177 |
-
"normalized": true,
|
| 178 |
-
"rstrip": false,
|
| 179 |
-
"single_word": false,
|
| 180 |
-
"special": false
|
| 181 |
-
},
|
| 182 |
-
"60242": {
|
| 183 |
-
"content": "<|future_token_51|>",
|
| 184 |
-
"lstrip": false,
|
| 185 |
-
"normalized": true,
|
| 186 |
-
"rstrip": false,
|
| 187 |
-
"single_word": false,
|
| 188 |
-
"special": false
|
| 189 |
-
},
|
| 190 |
-
"60243": {
|
| 191 |
-
"content": "<|future_token_52|>",
|
| 192 |
-
"lstrip": false,
|
| 193 |
-
"normalized": true,
|
| 194 |
-
"rstrip": false,
|
| 195 |
-
"single_word": false,
|
| 196 |
-
"special": false
|
| 197 |
-
},
|
| 198 |
-
"60244": {
|
| 199 |
-
"content": "<|future_token_53|>",
|
| 200 |
-
"lstrip": false,
|
| 201 |
-
"normalized": true,
|
| 202 |
-
"rstrip": false,
|
| 203 |
-
"single_word": false,
|
| 204 |
-
"special": false
|
| 205 |
-
},
|
| 206 |
-
"60245": {
|
| 207 |
-
"content": "<|future_token_54|>",
|
| 208 |
-
"lstrip": false,
|
| 209 |
-
"normalized": true,
|
| 210 |
-
"rstrip": false,
|
| 211 |
-
"single_word": false,
|
| 212 |
-
"special": false
|
| 213 |
-
},
|
| 214 |
-
"60246": {
|
| 215 |
-
"content": "<|future_token_55|>",
|
| 216 |
-
"lstrip": false,
|
| 217 |
-
"normalized": true,
|
| 218 |
-
"rstrip": false,
|
| 219 |
-
"single_word": false,
|
| 220 |
-
"special": false
|
| 221 |
-
},
|
| 222 |
-
"60247": {
|
| 223 |
-
"content": "<|future_token_56|>",
|
| 224 |
-
"lstrip": false,
|
| 225 |
-
"normalized": true,
|
| 226 |
-
"rstrip": false,
|
| 227 |
-
"single_word": false,
|
| 228 |
-
"special": false
|
| 229 |
-
},
|
| 230 |
-
"60248": {
|
| 231 |
-
"content": "<|future_token_57|>",
|
| 232 |
-
"lstrip": false,
|
| 233 |
-
"normalized": true,
|
| 234 |
-
"rstrip": false,
|
| 235 |
-
"single_word": false,
|
| 236 |
-
"special": false
|
| 237 |
-
},
|
| 238 |
-
"60249": {
|
| 239 |
-
"content": "<|future_token_58|>",
|
| 240 |
-
"lstrip": false,
|
| 241 |
-
"normalized": true,
|
| 242 |
-
"rstrip": false,
|
| 243 |
-
"single_word": false,
|
| 244 |
-
"special": false
|
| 245 |
-
},
|
| 246 |
-
"60250": {
|
| 247 |
-
"content": "<|future_token_59|>",
|
| 248 |
-
"lstrip": false,
|
| 249 |
-
"normalized": true,
|
| 250 |
-
"rstrip": false,
|
| 251 |
-
"single_word": false,
|
| 252 |
-
"special": false
|
| 253 |
-
},
|
| 254 |
-
"60251": {
|
| 255 |
-
"content": "<|future_token_60|>",
|
| 256 |
-
"lstrip": false,
|
| 257 |
-
"normalized": true,
|
| 258 |
-
"rstrip": false,
|
| 259 |
-
"single_word": false,
|
| 260 |
-
"special": false
|
| 261 |
-
},
|
| 262 |
-
"60252": {
|
| 263 |
-
"content": "<|future_token_61|>",
|
| 264 |
-
"lstrip": false,
|
| 265 |
-
"normalized": true,
|
| 266 |
-
"rstrip": false,
|
| 267 |
-
"single_word": false,
|
| 268 |
-
"special": false
|
| 269 |
-
},
|
| 270 |
-
"60253": {
|
| 271 |
-
"content": "<|future_token_62|>",
|
| 272 |
-
"lstrip": false,
|
| 273 |
-
"normalized": true,
|
| 274 |
-
"rstrip": false,
|
| 275 |
-
"single_word": false,
|
| 276 |
-
"special": false
|
| 277 |
-
},
|
| 278 |
-
"60254": {
|
| 279 |
-
"content": "<|future_token_63|>",
|
| 280 |
-
"lstrip": false,
|
| 281 |
-
"normalized": true,
|
| 282 |
-
"rstrip": false,
|
| 283 |
-
"single_word": false,
|
| 284 |
-
"special": false
|
| 285 |
-
},
|
| 286 |
-
"60255": {
|
| 287 |
-
"content": "<|future_token_64|>",
|
| 288 |
-
"lstrip": false,
|
| 289 |
-
"normalized": true,
|
| 290 |
-
"rstrip": false,
|
| 291 |
-
"single_word": false,
|
| 292 |
-
"special": false
|
| 293 |
-
},
|
| 294 |
-
"60256": {
|
| 295 |
"content": "<|im_start|>",
|
| 296 |
"lstrip": false,
|
| 297 |
"normalized": false,
|
|
@@ -299,7 +34,7 @@
|
|
| 299 |
"single_word": false,
|
| 300 |
"special": true
|
| 301 |
},
|
| 302 |
-
"
|
| 303 |
"content": "<|im_end|>",
|
| 304 |
"lstrip": false,
|
| 305 |
"normalized": false,
|
|
@@ -317,8 +52,8 @@
|
|
| 317 |
"clean_up_tokenization_spaces": false,
|
| 318 |
"eos_token": "</s>",
|
| 319 |
"legacy": true,
|
| 320 |
-
"model_max_length":
|
| 321 |
-
"pad_token": "
|
| 322 |
"sp_model_kwargs": {},
|
| 323 |
"spaces_between_special_tokens": false,
|
| 324 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
| 7 |
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
|
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
|
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
+
"40000": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"content": "<|im_start|>",
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": false,
|
|
|
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
| 36 |
},
|
| 37 |
+
"40001": {
|
| 38 |
"content": "<|im_end|>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
|
|
|
| 52 |
"clean_up_tokenization_spaces": false,
|
| 53 |
"eos_token": "</s>",
|
| 54 |
"legacy": true,
|
| 55 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 56 |
+
"pad_token": "<unk>",
|
| 57 |
"sp_model_kwargs": {},
|
| 58 |
"spaces_between_special_tokens": false,
|
| 59 |
"tokenizer_class": "LlamaTokenizer",
|