Commit
•
038a864
1
Parent(s):
dd1a681
Upload tokenizer
Browse files- tokenizer.json +14 -2
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 64,
|
| 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,
|
tokenizer_config.json
CHANGED
|
@@ -46,11 +46,18 @@
|
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
|
|
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 50 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 51 |
"sep_token": "[SEP]",
|
|
|
|
| 52 |
"strip_accents": null,
|
| 53 |
"tokenize_chinese_chars": true,
|
| 54 |
"tokenizer_class": "MobileBertTokenizer",
|
|
|
|
|
|
|
| 55 |
"unk_token": "[UNK]"
|
| 56 |
}
|
|
|
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 64,
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
"pad_token": "[PAD]",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
"sep_token": "[SEP]",
|
| 56 |
+
"stride": 0,
|
| 57 |
"strip_accents": null,
|
| 58 |
"tokenize_chinese_chars": true,
|
| 59 |
"tokenizer_class": "MobileBertTokenizer",
|
| 60 |
+
"truncation_side": "right",
|
| 61 |
+
"truncation_strategy": "longest_first",
|
| 62 |
"unk_token": "[UNK]"
|
| 63 |
}
|