Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +2 -2
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": "BatchLongest",
|
| 11 |
"direction": "Right",
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": {
|
| 5 |
"strategy": "BatchLongest",
|
| 6 |
"direction": "Right",
|
tokenizer_config.json
CHANGED
|
@@ -45,11 +45,11 @@
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_lower_case": true,
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
-
"model_max_length":
|
| 49 |
"pad_token": "[PAD]",
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
"strip_accents": null,
|
| 52 |
"tokenize_chinese_chars": true,
|
| 53 |
-
"tokenizer_class": "
|
| 54 |
"unk_token": "[UNK]"
|
| 55 |
}
|
|
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_lower_case": true,
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
"pad_token": "[PAD]",
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
"strip_accents": null,
|
| 52 |
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "MobileBertTokenizer",
|
| 54 |
"unk_token": "[UNK]"
|
| 55 |
}
|