Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer.json +27 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[DE]",
|
| 4 |
+
"[FR]",
|
| 5 |
+
"[ES]"
|
| 6 |
+
],
|
| 7 |
"cls_token": "[CLS]",
|
| 8 |
"mask_token": "[MASK]",
|
| 9 |
"pad_token": "[PAD]",
|
tokenizer.json
CHANGED
|
@@ -12,6 +12,33 @@
|
|
| 12 |
"normalized": false,
|
| 13 |
"special": true
|
| 14 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
{
|
| 16 |
"id": 100,
|
| 17 |
"content": "[UNK]",
|
|
|
|
| 12 |
"normalized": false,
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[ES]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[DE]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[FR]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
{
|
| 43 |
"id": 100,
|
| 44 |
"content": "[UNK]",
|