Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +2 -6
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": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -2,18 +2,14 @@
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": true,
|
| 5 |
-
"is_local":
|
| 6 |
"local_files_only": false,
|
| 7 |
"mask_token": "[MASK]",
|
| 8 |
-
"max_length": 512,
|
| 9 |
"model_max_length": 512,
|
| 10 |
"pad_token": "[PAD]",
|
| 11 |
"sep_token": "[SEP]",
|
| 12 |
-
"stride": 0,
|
| 13 |
"strip_accents": null,
|
| 14 |
"tokenize_chinese_chars": true,
|
| 15 |
-
"tokenizer_class": "
|
| 16 |
-
"truncation_side": "right",
|
| 17 |
-
"truncation_strategy": "longest_first",
|
| 18 |
"unk_token": "[UNK]"
|
| 19 |
}
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
"local_files_only": false,
|
| 7 |
"mask_token": "[MASK]",
|
|
|
|
| 8 |
"model_max_length": 512,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
|
|
|
| 11 |
"strip_accents": null,
|
| 12 |
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "DistilBertTokenizer",
|
|
|
|
|
|
|
| 14 |
"unk_token": "[UNK]"
|
| 15 |
}
|