Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
tokenizer_config.json
CHANGED
|
@@ -45,6 +45,7 @@
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
|
|
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"never_split": null,
|
|
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
"never_split": null,
|