Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +47 -130
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<|endoftext|>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"### End",
|
| 4 |
+
"### Instruction:",
|
| 5 |
+
"### Response:"
|
| 6 |
+
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
-
"
|
| 5 |
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
"normalized": false,
|
|
@@ -9,63 +9,15 @@
|
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
-
"
|
| 13 |
-
"content": "
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": true,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": false
|
| 19 |
-
},
|
| 20 |
-
"50258": {
|
| 21 |
-
"content": " ",
|
| 22 |
"lstrip": false,
|
| 23 |
-
"normalized":
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": false
|
| 27 |
-
},
|
| 28 |
-
"50259": {
|
| 29 |
-
"content": " ",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": true,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": false
|
| 35 |
-
},
|
| 36 |
-
"50260": {
|
| 37 |
-
"content": " ",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": true,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": false
|
| 43 |
-
},
|
| 44 |
-
"50261": {
|
| 45 |
-
"content": " ",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": true,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": false
|
| 51 |
-
},
|
| 52 |
-
"50262": {
|
| 53 |
-
"content": " ",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": true,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": false
|
| 59 |
-
},
|
| 60 |
-
"50263": {
|
| 61 |
-
"content": " ",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": true,
|
| 64 |
"rstrip": false,
|
| 65 |
"single_word": false,
|
| 66 |
-
"special":
|
| 67 |
},
|
| 68 |
-
"
|
| 69 |
"content": " ",
|
| 70 |
"lstrip": false,
|
| 71 |
"normalized": true,
|
|
@@ -73,7 +25,7 @@
|
|
| 73 |
"single_word": false,
|
| 74 |
"special": false
|
| 75 |
},
|
| 76 |
-
"
|
| 77 |
"content": " ",
|
| 78 |
"lstrip": false,
|
| 79 |
"normalized": true,
|
|
@@ -81,7 +33,7 @@
|
|
| 81 |
"single_word": false,
|
| 82 |
"special": false
|
| 83 |
},
|
| 84 |
-
"
|
| 85 |
"content": " ",
|
| 86 |
"lstrip": false,
|
| 87 |
"normalized": true,
|
|
@@ -89,7 +41,7 @@
|
|
| 89 |
"single_word": false,
|
| 90 |
"special": false
|
| 91 |
},
|
| 92 |
-
"
|
| 93 |
"content": " ",
|
| 94 |
"lstrip": false,
|
| 95 |
"normalized": true,
|
|
@@ -97,7 +49,7 @@
|
|
| 97 |
"single_word": false,
|
| 98 |
"special": false
|
| 99 |
},
|
| 100 |
-
"
|
| 101 |
"content": " ",
|
| 102 |
"lstrip": false,
|
| 103 |
"normalized": true,
|
|
@@ -105,7 +57,7 @@
|
|
| 105 |
"single_word": false,
|
| 106 |
"special": false
|
| 107 |
},
|
| 108 |
-
"
|
| 109 |
"content": " ",
|
| 110 |
"lstrip": false,
|
| 111 |
"normalized": true,
|
|
@@ -113,7 +65,7 @@
|
|
| 113 |
"single_word": false,
|
| 114 |
"special": false
|
| 115 |
},
|
| 116 |
-
"
|
| 117 |
"content": " ",
|
| 118 |
"lstrip": false,
|
| 119 |
"normalized": true,
|
|
@@ -121,7 +73,7 @@
|
|
| 121 |
"single_word": false,
|
| 122 |
"special": false
|
| 123 |
},
|
| 124 |
-
"
|
| 125 |
"content": " ",
|
| 126 |
"lstrip": false,
|
| 127 |
"normalized": true,
|
|
@@ -129,7 +81,7 @@
|
|
| 129 |
"single_word": false,
|
| 130 |
"special": false
|
| 131 |
},
|
| 132 |
-
"
|
| 133 |
"content": " ",
|
| 134 |
"lstrip": false,
|
| 135 |
"normalized": true,
|
|
@@ -137,7 +89,7 @@
|
|
| 137 |
"single_word": false,
|
| 138 |
"special": false
|
| 139 |
},
|
| 140 |
-
"
|
| 141 |
"content": " ",
|
| 142 |
"lstrip": false,
|
| 143 |
"normalized": true,
|
|
@@ -145,7 +97,7 @@
|
|
| 145 |
"single_word": false,
|
| 146 |
"special": false
|
| 147 |
},
|
| 148 |
-
"
|
| 149 |
"content": " ",
|
| 150 |
"lstrip": false,
|
| 151 |
"normalized": true,
|
|
@@ -153,7 +105,7 @@
|
|
| 153 |
"single_word": false,
|
| 154 |
"special": false
|
| 155 |
},
|
| 156 |
-
"
|
| 157 |
"content": " ",
|
| 158 |
"lstrip": false,
|
| 159 |
"normalized": true,
|
|
@@ -161,7 +113,7 @@
|
|
| 161 |
"single_word": false,
|
| 162 |
"special": false
|
| 163 |
},
|
| 164 |
-
"
|
| 165 |
"content": " ",
|
| 166 |
"lstrip": false,
|
| 167 |
"normalized": true,
|
|
@@ -169,7 +121,7 @@
|
|
| 169 |
"single_word": false,
|
| 170 |
"special": false
|
| 171 |
},
|
| 172 |
-
"
|
| 173 |
"content": " ",
|
| 174 |
"lstrip": false,
|
| 175 |
"normalized": true,
|
|
@@ -177,7 +129,7 @@
|
|
| 177 |
"single_word": false,
|
| 178 |
"special": false
|
| 179 |
},
|
| 180 |
-
"
|
| 181 |
"content": " ",
|
| 182 |
"lstrip": false,
|
| 183 |
"normalized": true,
|
|
@@ -185,7 +137,7 @@
|
|
| 185 |
"single_word": false,
|
| 186 |
"special": false
|
| 187 |
},
|
| 188 |
-
"
|
| 189 |
"content": " ",
|
| 190 |
"lstrip": false,
|
| 191 |
"normalized": true,
|
|
@@ -193,7 +145,7 @@
|
|
| 193 |
"single_word": false,
|
| 194 |
"special": false
|
| 195 |
},
|
| 196 |
-
"
|
| 197 |
"content": " ",
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": true,
|
|
@@ -201,7 +153,7 @@
|
|
| 201 |
"single_word": false,
|
| 202 |
"special": false
|
| 203 |
},
|
| 204 |
-
"
|
| 205 |
"content": " ",
|
| 206 |
"lstrip": false,
|
| 207 |
"normalized": true,
|
|
@@ -209,7 +161,7 @@
|
|
| 209 |
"single_word": false,
|
| 210 |
"special": false
|
| 211 |
},
|
| 212 |
-
"
|
| 213 |
"content": " ",
|
| 214 |
"lstrip": false,
|
| 215 |
"normalized": true,
|
|
@@ -217,7 +169,7 @@
|
|
| 217 |
"single_word": false,
|
| 218 |
"special": false
|
| 219 |
},
|
| 220 |
-
"
|
| 221 |
"content": " ",
|
| 222 |
"lstrip": false,
|
| 223 |
"normalized": true,
|
|
@@ -225,7 +177,7 @@
|
|
| 225 |
"single_word": false,
|
| 226 |
"special": false
|
| 227 |
},
|
| 228 |
-
"
|
| 229 |
"content": " ",
|
| 230 |
"lstrip": false,
|
| 231 |
"normalized": true,
|
|
@@ -233,7 +185,7 @@
|
|
| 233 |
"single_word": false,
|
| 234 |
"special": false
|
| 235 |
},
|
| 236 |
-
"
|
| 237 |
"content": " ",
|
| 238 |
"lstrip": false,
|
| 239 |
"normalized": true,
|
|
@@ -241,7 +193,7 @@
|
|
| 241 |
"single_word": false,
|
| 242 |
"special": false
|
| 243 |
},
|
| 244 |
-
"
|
| 245 |
"content": " ",
|
| 246 |
"lstrip": false,
|
| 247 |
"normalized": true,
|
|
@@ -249,76 +201,41 @@
|
|
| 249 |
"single_word": false,
|
| 250 |
"special": false
|
| 251 |
},
|
| 252 |
-
"
|
| 253 |
-
"content": "
|
| 254 |
-
"lstrip": false,
|
| 255 |
-
"normalized": true,
|
| 256 |
-
"rstrip": false,
|
| 257 |
-
"single_word": false,
|
| 258 |
-
"special": false
|
| 259 |
-
},
|
| 260 |
-
"50288": {
|
| 261 |
-
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
-
"lstrip": false,
|
| 263 |
-
"normalized": true,
|
| 264 |
-
"rstrip": false,
|
| 265 |
-
"single_word": false,
|
| 266 |
-
"special": false
|
| 267 |
-
},
|
| 268 |
-
"50289": {
|
| 269 |
-
"content": "\t\t\t\t\t\t\t",
|
| 270 |
-
"lstrip": false,
|
| 271 |
-
"normalized": true,
|
| 272 |
-
"rstrip": false,
|
| 273 |
-
"single_word": false,
|
| 274 |
-
"special": false
|
| 275 |
-
},
|
| 276 |
-
"50290": {
|
| 277 |
-
"content": "\t\t\t\t\t\t",
|
| 278 |
-
"lstrip": false,
|
| 279 |
-
"normalized": true,
|
| 280 |
-
"rstrip": false,
|
| 281 |
-
"single_word": false,
|
| 282 |
-
"special": false
|
| 283 |
-
},
|
| 284 |
-
"50291": {
|
| 285 |
-
"content": "\t\t\t\t\t",
|
| 286 |
-
"lstrip": false,
|
| 287 |
-
"normalized": true,
|
| 288 |
-
"rstrip": false,
|
| 289 |
-
"single_word": false,
|
| 290 |
-
"special": false
|
| 291 |
-
},
|
| 292 |
-
"50292": {
|
| 293 |
-
"content": "\t\t\t\t",
|
| 294 |
"lstrip": false,
|
| 295 |
-
"normalized":
|
| 296 |
"rstrip": false,
|
| 297 |
"single_word": false,
|
| 298 |
-
"special":
|
| 299 |
},
|
| 300 |
-
"
|
| 301 |
-
"content": "
|
| 302 |
"lstrip": false,
|
| 303 |
-
"normalized":
|
| 304 |
"rstrip": false,
|
| 305 |
"single_word": false,
|
| 306 |
-
"special":
|
| 307 |
},
|
| 308 |
-
"
|
| 309 |
-
"content": "
|
| 310 |
"lstrip": false,
|
| 311 |
-
"normalized":
|
| 312 |
"rstrip": false,
|
| 313 |
"single_word": false,
|
| 314 |
-
"special":
|
| 315 |
}
|
| 316 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 317 |
"bos_token": "<|endoftext|>",
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
"eos_token": "<|endoftext|>",
|
| 320 |
-
"model_max_length":
|
| 321 |
"pad_token": "<|endoftext|>",
|
| 322 |
-
"tokenizer_class": "
|
| 323 |
"unk_token": "<|endoftext|>"
|
| 324 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
"normalized": false,
|
|
|
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|padding|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
},
|
| 20 |
+
"50254": {
|
| 21 |
"content": " ",
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": true,
|
|
|
|
| 25 |
"single_word": false,
|
| 26 |
"special": false
|
| 27 |
},
|
| 28 |
+
"50255": {
|
| 29 |
"content": " ",
|
| 30 |
"lstrip": false,
|
| 31 |
"normalized": true,
|
|
|
|
| 33 |
"single_word": false,
|
| 34 |
"special": false
|
| 35 |
},
|
| 36 |
+
"50256": {
|
| 37 |
"content": " ",
|
| 38 |
"lstrip": false,
|
| 39 |
"normalized": true,
|
|
|
|
| 41 |
"single_word": false,
|
| 42 |
"special": false
|
| 43 |
},
|
| 44 |
+
"50257": {
|
| 45 |
"content": " ",
|
| 46 |
"lstrip": false,
|
| 47 |
"normalized": true,
|
|
|
|
| 49 |
"single_word": false,
|
| 50 |
"special": false
|
| 51 |
},
|
| 52 |
+
"50258": {
|
| 53 |
"content": " ",
|
| 54 |
"lstrip": false,
|
| 55 |
"normalized": true,
|
|
|
|
| 57 |
"single_word": false,
|
| 58 |
"special": false
|
| 59 |
},
|
| 60 |
+
"50259": {
|
| 61 |
"content": " ",
|
| 62 |
"lstrip": false,
|
| 63 |
"normalized": true,
|
|
|
|
| 65 |
"single_word": false,
|
| 66 |
"special": false
|
| 67 |
},
|
| 68 |
+
"50260": {
|
| 69 |
"content": " ",
|
| 70 |
"lstrip": false,
|
| 71 |
"normalized": true,
|
|
|
|
| 73 |
"single_word": false,
|
| 74 |
"special": false
|
| 75 |
},
|
| 76 |
+
"50261": {
|
| 77 |
"content": " ",
|
| 78 |
"lstrip": false,
|
| 79 |
"normalized": true,
|
|
|
|
| 81 |
"single_word": false,
|
| 82 |
"special": false
|
| 83 |
},
|
| 84 |
+
"50262": {
|
| 85 |
"content": " ",
|
| 86 |
"lstrip": false,
|
| 87 |
"normalized": true,
|
|
|
|
| 89 |
"single_word": false,
|
| 90 |
"special": false
|
| 91 |
},
|
| 92 |
+
"50263": {
|
| 93 |
"content": " ",
|
| 94 |
"lstrip": false,
|
| 95 |
"normalized": true,
|
|
|
|
| 97 |
"single_word": false,
|
| 98 |
"special": false
|
| 99 |
},
|
| 100 |
+
"50264": {
|
| 101 |
"content": " ",
|
| 102 |
"lstrip": false,
|
| 103 |
"normalized": true,
|
|
|
|
| 105 |
"single_word": false,
|
| 106 |
"special": false
|
| 107 |
},
|
| 108 |
+
"50265": {
|
| 109 |
"content": " ",
|
| 110 |
"lstrip": false,
|
| 111 |
"normalized": true,
|
|
|
|
| 113 |
"single_word": false,
|
| 114 |
"special": false
|
| 115 |
},
|
| 116 |
+
"50266": {
|
| 117 |
"content": " ",
|
| 118 |
"lstrip": false,
|
| 119 |
"normalized": true,
|
|
|
|
| 121 |
"single_word": false,
|
| 122 |
"special": false
|
| 123 |
},
|
| 124 |
+
"50267": {
|
| 125 |
"content": " ",
|
| 126 |
"lstrip": false,
|
| 127 |
"normalized": true,
|
|
|
|
| 129 |
"single_word": false,
|
| 130 |
"special": false
|
| 131 |
},
|
| 132 |
+
"50268": {
|
| 133 |
"content": " ",
|
| 134 |
"lstrip": false,
|
| 135 |
"normalized": true,
|
|
|
|
| 137 |
"single_word": false,
|
| 138 |
"special": false
|
| 139 |
},
|
| 140 |
+
"50269": {
|
| 141 |
"content": " ",
|
| 142 |
"lstrip": false,
|
| 143 |
"normalized": true,
|
|
|
|
| 145 |
"single_word": false,
|
| 146 |
"special": false
|
| 147 |
},
|
| 148 |
+
"50270": {
|
| 149 |
"content": " ",
|
| 150 |
"lstrip": false,
|
| 151 |
"normalized": true,
|
|
|
|
| 153 |
"single_word": false,
|
| 154 |
"special": false
|
| 155 |
},
|
| 156 |
+
"50271": {
|
| 157 |
"content": " ",
|
| 158 |
"lstrip": false,
|
| 159 |
"normalized": true,
|
|
|
|
| 161 |
"single_word": false,
|
| 162 |
"special": false
|
| 163 |
},
|
| 164 |
+
"50272": {
|
| 165 |
"content": " ",
|
| 166 |
"lstrip": false,
|
| 167 |
"normalized": true,
|
|
|
|
| 169 |
"single_word": false,
|
| 170 |
"special": false
|
| 171 |
},
|
| 172 |
+
"50273": {
|
| 173 |
"content": " ",
|
| 174 |
"lstrip": false,
|
| 175 |
"normalized": true,
|
|
|
|
| 177 |
"single_word": false,
|
| 178 |
"special": false
|
| 179 |
},
|
| 180 |
+
"50274": {
|
| 181 |
"content": " ",
|
| 182 |
"lstrip": false,
|
| 183 |
"normalized": true,
|
|
|
|
| 185 |
"single_word": false,
|
| 186 |
"special": false
|
| 187 |
},
|
| 188 |
+
"50275": {
|
| 189 |
"content": " ",
|
| 190 |
"lstrip": false,
|
| 191 |
"normalized": true,
|
|
|
|
| 193 |
"single_word": false,
|
| 194 |
"special": false
|
| 195 |
},
|
| 196 |
+
"50276": {
|
| 197 |
"content": " ",
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": true,
|
|
|
|
| 201 |
"single_word": false,
|
| 202 |
"special": false
|
| 203 |
},
|
| 204 |
+
"50277": {
|
| 205 |
+
"content": "### End",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
"rstrip": false,
|
| 209 |
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
},
|
| 212 |
+
"50278": {
|
| 213 |
+
"content": "### Instruction:",
|
| 214 |
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
"rstrip": false,
|
| 217 |
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
},
|
| 220 |
+
"50279": {
|
| 221 |
+
"content": "### Response:",
|
| 222 |
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
"rstrip": false,
|
| 225 |
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
}
|
| 228 |
},
|
| 229 |
+
"additional_special_tokens": [
|
| 230 |
+
"### End",
|
| 231 |
+
"### Instruction:",
|
| 232 |
+
"### Response:"
|
| 233 |
+
],
|
| 234 |
"bos_token": "<|endoftext|>",
|
| 235 |
"clean_up_tokenization_spaces": true,
|
| 236 |
"eos_token": "<|endoftext|>",
|
| 237 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 238 |
"pad_token": "<|endoftext|>",
|
| 239 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 240 |
"unk_token": "<|endoftext|>"
|
| 241 |
}
|