update tokenizer
Browse files- README.md +2 -2
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -41
README.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
license: apache-2.0
|
| 5 |
-
datasets:
|
| 6 |
-
- BEE-spoke-data/bees-internal
|
| 7 |
---
|
| 8 |
|
| 9 |
# BeeTokenizer
|
|
|
|
| 1 |
---
|
| 2 |
+
datasets:
|
| 3 |
+
- BEE-spoke-data/bees-internal
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
license: apache-2.0
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# BeeTokenizer
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": {
|
| 3 |
"content": "<cls>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<bos>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<cls>",
|
| 11 |
"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 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "<
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
@@ -17,14 +17,6 @@
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
"content": "<unk>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
@@ -32,7 +24,7 @@
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
"content": "<cls>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
@@ -40,7 +32,7 @@
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
"content": "<sep>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
|
@@ -48,7 +40,7 @@
|
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
-
"
|
| 52 |
"content": "<mask>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
@@ -56,7 +48,7 @@
|
|
| 56 |
"single_word": false,
|
| 57 |
"special": true
|
| 58 |
},
|
| 59 |
-
"
|
| 60 |
"content": "<|endoftext|>",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": false,
|
|
@@ -64,7 +56,7 @@
|
|
| 64 |
"single_word": false,
|
| 65 |
"special": true
|
| 66 |
},
|
| 67 |
-
"
|
| 68 |
"content": " ",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": true,
|
|
@@ -72,7 +64,7 @@
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": false
|
| 74 |
},
|
| 75 |
-
"
|
| 76 |
"content": " ",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": true,
|
|
@@ -80,7 +72,7 @@
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": false
|
| 82 |
},
|
| 83 |
-
"
|
| 84 |
"content": " ",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": true,
|
|
@@ -88,7 +80,7 @@
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": false
|
| 90 |
},
|
| 91 |
-
"
|
| 92 |
"content": " ",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": true,
|
|
@@ -96,7 +88,7 @@
|
|
| 96 |
"single_word": false,
|
| 97 |
"special": false
|
| 98 |
},
|
| 99 |
-
"
|
| 100 |
"content": " ",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": true,
|
|
@@ -104,7 +96,7 @@
|
|
| 104 |
"single_word": false,
|
| 105 |
"special": false
|
| 106 |
},
|
| 107 |
-
"
|
| 108 |
"content": " ",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": true,
|
|
@@ -112,7 +104,7 @@
|
|
| 112 |
"single_word": false,
|
| 113 |
"special": false
|
| 114 |
},
|
| 115 |
-
"
|
| 116 |
"content": " ",
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": true,
|
|
@@ -120,7 +112,7 @@
|
|
| 120 |
"single_word": false,
|
| 121 |
"special": false
|
| 122 |
},
|
| 123 |
-
"
|
| 124 |
"content": " ",
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": true,
|
|
@@ -128,7 +120,7 @@
|
|
| 128 |
"single_word": false,
|
| 129 |
"special": false
|
| 130 |
},
|
| 131 |
-
"
|
| 132 |
"content": " ",
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": true,
|
|
@@ -136,7 +128,7 @@
|
|
| 136 |
"single_word": false,
|
| 137 |
"special": false
|
| 138 |
},
|
| 139 |
-
"
|
| 140 |
"content": " ",
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": true,
|
|
@@ -144,7 +136,7 @@
|
|
| 144 |
"single_word": false,
|
| 145 |
"special": false
|
| 146 |
},
|
| 147 |
-
"
|
| 148 |
"content": " ",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": true,
|
|
@@ -152,7 +144,7 @@
|
|
| 152 |
"single_word": false,
|
| 153 |
"special": false
|
| 154 |
},
|
| 155 |
-
"
|
| 156 |
"content": " ",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": true,
|
|
@@ -160,7 +152,7 @@
|
|
| 160 |
"single_word": false,
|
| 161 |
"special": false
|
| 162 |
},
|
| 163 |
-
"
|
| 164 |
"content": " ",
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": true,
|
|
@@ -168,7 +160,7 @@
|
|
| 168 |
"single_word": false,
|
| 169 |
"special": false
|
| 170 |
},
|
| 171 |
-
"
|
| 172 |
"content": " ",
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": true,
|
|
@@ -176,7 +168,7 @@
|
|
| 176 |
"single_word": false,
|
| 177 |
"special": false
|
| 178 |
},
|
| 179 |
-
"
|
| 180 |
"content": " ",
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": true,
|
|
@@ -184,7 +176,7 @@
|
|
| 184 |
"single_word": false,
|
| 185 |
"special": false
|
| 186 |
},
|
| 187 |
-
"
|
| 188 |
"content": " ",
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": true,
|
|
@@ -192,7 +184,7 @@
|
|
| 192 |
"single_word": false,
|
| 193 |
"special": false
|
| 194 |
},
|
| 195 |
-
"
|
| 196 |
"content": " ",
|
| 197 |
"lstrip": false,
|
| 198 |
"normalized": true,
|
|
@@ -200,7 +192,7 @@
|
|
| 200 |
"single_word": false,
|
| 201 |
"special": false
|
| 202 |
},
|
| 203 |
-
"
|
| 204 |
"content": " ",
|
| 205 |
"lstrip": false,
|
| 206 |
"normalized": true,
|
|
@@ -208,7 +200,7 @@
|
|
| 208 |
"single_word": false,
|
| 209 |
"special": false
|
| 210 |
},
|
| 211 |
-
"
|
| 212 |
"content": " ",
|
| 213 |
"lstrip": false,
|
| 214 |
"normalized": true,
|
|
@@ -216,7 +208,7 @@
|
|
| 216 |
"single_word": false,
|
| 217 |
"special": false
|
| 218 |
},
|
| 219 |
-
"
|
| 220 |
"content": " ",
|
| 221 |
"lstrip": false,
|
| 222 |
"normalized": true,
|
|
@@ -224,7 +216,7 @@
|
|
| 224 |
"single_word": false,
|
| 225 |
"special": false
|
| 226 |
},
|
| 227 |
-
"
|
| 228 |
"content": " ",
|
| 229 |
"lstrip": false,
|
| 230 |
"normalized": true,
|
|
@@ -232,7 +224,7 @@
|
|
| 232 |
"single_word": false,
|
| 233 |
"special": false
|
| 234 |
},
|
| 235 |
-
"
|
| 236 |
"content": " ",
|
| 237 |
"lstrip": false,
|
| 238 |
"normalized": true,
|
|
@@ -240,7 +232,7 @@
|
|
| 240 |
"single_word": false,
|
| 241 |
"special": false
|
| 242 |
},
|
| 243 |
-
"
|
| 244 |
"content": " ",
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": true,
|
|
@@ -248,7 +240,7 @@
|
|
| 248 |
"single_word": false,
|
| 249 |
"special": false
|
| 250 |
},
|
| 251 |
-
"
|
| 252 |
"content": " ",
|
| 253 |
"lstrip": false,
|
| 254 |
"normalized": true,
|
|
@@ -256,7 +248,7 @@
|
|
| 256 |
"single_word": false,
|
| 257 |
"special": false
|
| 258 |
},
|
| 259 |
-
"
|
| 260 |
"content": " ",
|
| 261 |
"lstrip": false,
|
| 262 |
"normalized": true,
|
|
@@ -264,7 +256,7 @@
|
|
| 264 |
"single_word": false,
|
| 265 |
"special": false
|
| 266 |
},
|
| 267 |
-
"
|
| 268 |
"content": " ",
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": true,
|
|
@@ -272,7 +264,7 @@
|
|
| 272 |
"single_word": false,
|
| 273 |
"special": false
|
| 274 |
},
|
| 275 |
-
"
|
| 276 |
"content": " ",
|
| 277 |
"lstrip": false,
|
| 278 |
"normalized": true,
|
|
@@ -280,7 +272,7 @@
|
|
| 280 |
"single_word": false,
|
| 281 |
"special": false
|
| 282 |
},
|
| 283 |
-
"
|
| 284 |
"content": " ",
|
| 285 |
"lstrip": false,
|
| 286 |
"normalized": true,
|
|
@@ -289,6 +281,7 @@
|
|
| 289 |
"special": false
|
| 290 |
}
|
| 291 |
},
|
|
|
|
| 292 |
"clean_up_tokenization_spaces": true,
|
| 293 |
"cls_token": "<cls>",
|
| 294 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"content": "<unk>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"3": {
|
| 28 |
"content": "<cls>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"4": {
|
| 36 |
"content": "<sep>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
+
"5": {
|
| 44 |
"content": "<mask>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
|
|
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
+
"6": {
|
| 52 |
"content": "<|endoftext|>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
|
|
| 56 |
"single_word": false,
|
| 57 |
"special": true
|
| 58 |
},
|
| 59 |
+
"31972": {
|
| 60 |
"content": " ",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": true,
|
|
|
|
| 64 |
"single_word": false,
|
| 65 |
"special": false
|
| 66 |
},
|
| 67 |
+
"31973": {
|
| 68 |
"content": " ",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": true,
|
|
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": false
|
| 74 |
},
|
| 75 |
+
"31974": {
|
| 76 |
"content": " ",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": true,
|
|
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": false
|
| 82 |
},
|
| 83 |
+
"31975": {
|
| 84 |
"content": " ",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": true,
|
|
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": false
|
| 90 |
},
|
| 91 |
+
"31976": {
|
| 92 |
"content": " ",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": true,
|
|
|
|
| 96 |
"single_word": false,
|
| 97 |
"special": false
|
| 98 |
},
|
| 99 |
+
"31977": {
|
| 100 |
"content": " ",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": true,
|
|
|
|
| 104 |
"single_word": false,
|
| 105 |
"special": false
|
| 106 |
},
|
| 107 |
+
"31978": {
|
| 108 |
"content": " ",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": true,
|
|
|
|
| 112 |
"single_word": false,
|
| 113 |
"special": false
|
| 114 |
},
|
| 115 |
+
"31979": {
|
| 116 |
"content": " ",
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": true,
|
|
|
|
| 120 |
"single_word": false,
|
| 121 |
"special": false
|
| 122 |
},
|
| 123 |
+
"31980": {
|
| 124 |
"content": " ",
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": true,
|
|
|
|
| 128 |
"single_word": false,
|
| 129 |
"special": false
|
| 130 |
},
|
| 131 |
+
"31981": {
|
| 132 |
"content": " ",
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": true,
|
|
|
|
| 136 |
"single_word": false,
|
| 137 |
"special": false
|
| 138 |
},
|
| 139 |
+
"31982": {
|
| 140 |
"content": " ",
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": true,
|
|
|
|
| 144 |
"single_word": false,
|
| 145 |
"special": false
|
| 146 |
},
|
| 147 |
+
"31983": {
|
| 148 |
"content": " ",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": true,
|
|
|
|
| 152 |
"single_word": false,
|
| 153 |
"special": false
|
| 154 |
},
|
| 155 |
+
"31984": {
|
| 156 |
"content": " ",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": true,
|
|
|
|
| 160 |
"single_word": false,
|
| 161 |
"special": false
|
| 162 |
},
|
| 163 |
+
"31985": {
|
| 164 |
"content": " ",
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": true,
|
|
|
|
| 168 |
"single_word": false,
|
| 169 |
"special": false
|
| 170 |
},
|
| 171 |
+
"31986": {
|
| 172 |
"content": " ",
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": true,
|
|
|
|
| 176 |
"single_word": false,
|
| 177 |
"special": false
|
| 178 |
},
|
| 179 |
+
"31987": {
|
| 180 |
"content": " ",
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": true,
|
|
|
|
| 184 |
"single_word": false,
|
| 185 |
"special": false
|
| 186 |
},
|
| 187 |
+
"31988": {
|
| 188 |
"content": " ",
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": true,
|
|
|
|
| 192 |
"single_word": false,
|
| 193 |
"special": false
|
| 194 |
},
|
| 195 |
+
"31989": {
|
| 196 |
"content": " ",
|
| 197 |
"lstrip": false,
|
| 198 |
"normalized": true,
|
|
|
|
| 200 |
"single_word": false,
|
| 201 |
"special": false
|
| 202 |
},
|
| 203 |
+
"31990": {
|
| 204 |
"content": " ",
|
| 205 |
"lstrip": false,
|
| 206 |
"normalized": true,
|
|
|
|
| 208 |
"single_word": false,
|
| 209 |
"special": false
|
| 210 |
},
|
| 211 |
+
"31991": {
|
| 212 |
"content": " ",
|
| 213 |
"lstrip": false,
|
| 214 |
"normalized": true,
|
|
|
|
| 216 |
"single_word": false,
|
| 217 |
"special": false
|
| 218 |
},
|
| 219 |
+
"31992": {
|
| 220 |
"content": " ",
|
| 221 |
"lstrip": false,
|
| 222 |
"normalized": true,
|
|
|
|
| 224 |
"single_word": false,
|
| 225 |
"special": false
|
| 226 |
},
|
| 227 |
+
"31993": {
|
| 228 |
"content": " ",
|
| 229 |
"lstrip": false,
|
| 230 |
"normalized": true,
|
|
|
|
| 232 |
"single_word": false,
|
| 233 |
"special": false
|
| 234 |
},
|
| 235 |
+
"31994": {
|
| 236 |
"content": " ",
|
| 237 |
"lstrip": false,
|
| 238 |
"normalized": true,
|
|
|
|
| 240 |
"single_word": false,
|
| 241 |
"special": false
|
| 242 |
},
|
| 243 |
+
"31995": {
|
| 244 |
"content": " ",
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": true,
|
|
|
|
| 248 |
"single_word": false,
|
| 249 |
"special": false
|
| 250 |
},
|
| 251 |
+
"31996": {
|
| 252 |
"content": " ",
|
| 253 |
"lstrip": false,
|
| 254 |
"normalized": true,
|
|
|
|
| 256 |
"single_word": false,
|
| 257 |
"special": false
|
| 258 |
},
|
| 259 |
+
"31997": {
|
| 260 |
"content": " ",
|
| 261 |
"lstrip": false,
|
| 262 |
"normalized": true,
|
|
|
|
| 264 |
"single_word": false,
|
| 265 |
"special": false
|
| 266 |
},
|
| 267 |
+
"31998": {
|
| 268 |
"content": " ",
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": true,
|
|
|
|
| 272 |
"single_word": false,
|
| 273 |
"special": false
|
| 274 |
},
|
| 275 |
+
"31999": {
|
| 276 |
"content": " ",
|
| 277 |
"lstrip": false,
|
| 278 |
"normalized": true,
|
|
|
|
| 281 |
"special": false
|
| 282 |
}
|
| 283 |
},
|
| 284 |
+
"bos_token": "<bos>",
|
| 285 |
"clean_up_tokenization_spaces": true,
|
| 286 |
"cls_token": "<cls>",
|
| 287 |
"eos_token": "<|endoftext|>",
|