Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +2 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
|
|
|
| 4 |
"do_lower_case": false,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"model_max_length": 512,
|
|
|
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
"strip_accents": null,
|
|
|
|
| 1 |
{
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
"do_lower_case": false,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
"model_max_length": 512,
|
| 8 |
+
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
"strip_accents": null,
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|