Commit
•
a9a6562
1
Parent(s):
1604554
Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +8 -2
special_tokens_map.json
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1657,8 +1657,14 @@
|
|
| 1657 |
"special": true
|
| 1658 |
}
|
| 1659 |
},
|
|
|
|
| 1660 |
"clean_up_tokenization_spaces": true,
|
| 1661 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1662 |
"pad_token": "<pad>",
|
| 1663 |
-
"
|
|
|
|
|
|
|
| 1664 |
}
|
|
|
|
| 1657 |
"special": true
|
| 1658 |
}
|
| 1659 |
},
|
| 1660 |
+
"bos_token": "<s>",
|
| 1661 |
"clean_up_tokenization_spaces": true,
|
| 1662 |
+
"cls_token": "<s>",
|
| 1663 |
+
"eos_token": "</s>",
|
| 1664 |
+
"mask_token": "<mask>",
|
| 1665 |
+
"model_max_length": 1024,
|
| 1666 |
"pad_token": "<pad>",
|
| 1667 |
+
"sep_token": "</s>",
|
| 1668 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 1669 |
+
"unk_token": "<unk>"
|
| 1670 |
}
|