Upload tokenizer
Browse files- tokenizer.json +1 -8
- tokenizer_config.json +4 -0
tokenizer.json
CHANGED
|
@@ -6,14 +6,7 @@
|
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
-
"padding":
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 0,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "[PAD]"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
| 12 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -47,12 +47,16 @@
|
|
| 47 |
"do_lower_case": true,
|
| 48 |
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
|
|
|
| 50 |
"model_max_length": 512,
|
| 51 |
"never_split": null,
|
| 52 |
"pad_token": "[PAD]",
|
| 53 |
"sep_token": "[SEP]",
|
|
|
|
| 54 |
"strip_accents": null,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 57 |
"unk_token": "[UNK]"
|
| 58 |
}
|
|
|
|
| 47 |
"do_lower_case": true,
|
| 48 |
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
+
"max_length": 512,
|
| 51 |
"model_max_length": 512,
|
| 52 |
"never_split": null,
|
| 53 |
"pad_token": "[PAD]",
|
| 54 |
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
"strip_accents": null,
|
| 57 |
"tokenize_chinese_chars": true,
|
| 58 |
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
"unk_token": "[UNK]"
|
| 62 |
}
|