Commit ·
bb6fecd
1
Parent(s): 9c7c349
Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +2 -2
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f28365a3e63955d125594316e804645c13fdd23363ce35d2de07e7c2d4093de8
|
| 3 |
+
size 15273190
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "[CLS]",
|
|
|
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": true,
|
| 5 |
"eos_token": "[SEP]",
|
|
@@ -12,12 +13,11 @@
|
|
| 12 |
"rstrip": false,
|
| 13 |
"single_word": false
|
| 14 |
},
|
| 15 |
-
"model_max_length":
|
| 16 |
"pad_token": "<pad>",
|
| 17 |
"remove_space": true,
|
| 18 |
"sep_token": "[SEP]",
|
| 19 |
"sp_model_kwargs": {},
|
| 20 |
-
"special_tokens_map_file": null,
|
| 21 |
"tokenizer_class": "AlbertTokenizer",
|
| 22 |
"unk_token": "<unk>"
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "[CLS]",
|
| 5 |
"do_lower_case": true,
|
| 6 |
"eos_token": "[SEP]",
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"model_max_length": 512,
|
| 17 |
"pad_token": "<pad>",
|
| 18 |
"remove_space": true,
|
| 19 |
"sep_token": "[SEP]",
|
| 20 |
"sp_model_kwargs": {},
|
|
|
|
| 21 |
"tokenizer_class": "AlbertTokenizer",
|
| 22 |
"unk_token": "<unk>"
|
| 23 |
}
|