Commit ·
dca8b1a
1
Parent(s): 93da57d
Make the tokenizer config match that of the large and base versions (#11)
Browse files- Make the tokenizer config match that of the large and base versions (f9611f088d69fc3157ff1878217feee72bda0145)
Co-authored-by: Santiago Castro <bryant1410@users.noreply.huggingface.co>
- tokenizer_config.json +1 -3
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"do_basic_tokenize": true,
|
| 5 |
"do_lower_case": true,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
-
"model_max_length":
|
| 8 |
-
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
"strip_accents": null,
|
|
|
|
| 1 |
{
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
|
|
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
|
|
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
"strip_accents": null,
|