Upload tokenizer
Browse files- special_tokens_map.json +14 -2
- vocab.json +3 -4
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"pad_token":
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"pad_token": {
|
| 3 |
+
"content": "a",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"unk_token": {
|
| 10 |
+
"content": "<unk>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
}
|
vocab.json
CHANGED
|
@@ -26,6 +26,7 @@
|
|
| 26 |
"t": 6,
|
| 27 |
"u": 4,
|
| 28 |
"v": 32,
|
|
|
|
| 29 |
"x": 10,
|
| 30 |
"y": 16,
|
| 31 |
"z": 22,
|
|
@@ -33,12 +34,10 @@
|
|
| 33 |
"á": 14,
|
| 34 |
"é": 30,
|
| 35 |
"ì": 37,
|
| 36 |
-
"í":
|
| 37 |
"ï": 36,
|
| 38 |
"ñ": 34,
|
| 39 |
"ó": 27,
|
| 40 |
"ú": 21,
|
| 41 |
-
"̱": 1
|
| 42 |
-
"w": 40,
|
| 43 |
-
"í": 41
|
| 44 |
}
|
|
|
|
| 26 |
"t": 6,
|
| 27 |
"u": 4,
|
| 28 |
"v": 32,
|
| 29 |
+
"w": 40,
|
| 30 |
"x": 10,
|
| 31 |
"y": 16,
|
| 32 |
"z": 22,
|
|
|
|
| 34 |
"á": 14,
|
| 35 |
"é": 30,
|
| 36 |
"ì": 37,
|
| 37 |
+
"í": 41,
|
| 38 |
"ï": 36,
|
| 39 |
"ñ": 34,
|
| 40 |
"ó": 27,
|
| 41 |
"ú": 21,
|
| 42 |
+
"̱": 1
|
|
|
|
|
|
|
| 43 |
}
|