Commit
•
9ea1ca9
1
Parent(s):
8bf4851
Upload tokenizer
Browse files- added_tokens.json +3 -1
- tokenizer_config.json +16 -0
added_tokens.json
CHANGED
|
@@ -1,3 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"<unk>": 37
|
|
|
|
|
|
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<unk>": 37,
|
| 3 |
+
"æ": 38,
|
| 4 |
+
"ø": 39
|
| 5 |
}
|
tokenizer_config.json
CHANGED
|
@@ -16,6 +16,22 @@
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
},
|
| 21 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
+
},
|
| 20 |
+
"38": {
|
| 21 |
+
"content": "æ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"39": {
|
| 29 |
+
"content": "ø",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"clean_up_tokenization_spaces": true,
|