Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +0 -1
special_tokens_map.json
CHANGED
|
@@ -2,7 +2,13 @@
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
-
"mask_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"pad_token": "<pad>",
|
| 7 |
"sep_token": "</s>",
|
| 8 |
"unk_token": "<unk>"
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
"pad_token": "<pad>",
|
| 13 |
"sep_token": "</s>",
|
| 14 |
"unk_token": "<unk>"
|
tokenizer_config.json
CHANGED
|
@@ -42,7 +42,6 @@
|
|
| 42 |
"special": true
|
| 43 |
}
|
| 44 |
},
|
| 45 |
-
"additional_special_tokens": [],
|
| 46 |
"bos_token": "<s>",
|
| 47 |
"clean_up_tokenization_spaces": true,
|
| 48 |
"cls_token": "<s>",
|
|
|
|
| 42 |
"special": true
|
| 43 |
}
|
| 44 |
},
|
|
|
|
| 45 |
"bos_token": "<s>",
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|