Upload tokenizer
Browse files- added_tokens.json +1 -2
- tokenizer_config.json +1 -9
- vocab.json +1 -1
added_tokens.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
"</s>": 136,
|
| 3 |
-
"<s>": 135
|
| 4 |
-
"[UNK]": 137
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"</s>": 136,
|
| 3 |
+
"<s>": 135
|
|
|
|
| 4 |
}
|
tokenizer_config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"special": false
|
| 10 |
},
|
| 11 |
"134": {
|
| 12 |
-
"content": "[UNK",
|
| 13 |
"lstrip": true,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": true,
|
|
@@ -31,14 +31,6 @@
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
-
},
|
| 35 |
-
"137": {
|
| 36 |
-
"content": "[UNK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"bos_token": "<s>",
|
|
|
|
| 9 |
"special": false
|
| 10 |
},
|
| 11 |
"134": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
"lstrip": true,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": true,
|
|
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"bos_token": "<s>",
|
vocab.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"5": 104,
|
| 9 |
"6": 105,
|
| 10 |
"[PAD]": 133,
|
| 11 |
-
"[UNK": 134,
|
| 12 |
"a": 84,
|
| 13 |
"b": 1,
|
| 14 |
"c": 6,
|
|
|
|
| 8 |
"5": 104,
|
| 9 |
"6": 105,
|
| 10 |
"[PAD]": 133,
|
| 11 |
+
"[UNK]": 134,
|
| 12 |
"a": 84,
|
| 13 |
"b": 1,
|
| 14 |
"c": 6,
|