Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 128,
|
| 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
|
@@ -5,12 +5,19 @@
|
|
| 5 |
"do_lower_case": false,
|
| 6 |
"full_tokenizer_file": null,
|
| 7 |
"mask_token": "[MASK]",
|
|
|
|
| 8 |
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
"never_split": null,
|
|
|
|
| 10 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 11 |
"sep_token": "[SEP]",
|
|
|
|
| 12 |
"strip_accents": null,
|
| 13 |
"tokenize_chinese_chars": false,
|
| 14 |
"tokenizer_class": "ElectraTokenizer",
|
|
|
|
|
|
|
| 15 |
"unk_token": "[UNK]"
|
| 16 |
}
|
|
|
|
| 5 |
"do_lower_case": false,
|
| 6 |
"full_tokenizer_file": null,
|
| 7 |
"mask_token": "[MASK]",
|
| 8 |
+
"max_length": 512,
|
| 9 |
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
"never_split": null,
|
| 11 |
+
"pad_to_multiple_of": null,
|
| 12 |
"pad_token": "[PAD]",
|
| 13 |
+
"pad_token_type_id": 0,
|
| 14 |
+
"padding_side": "right",
|
| 15 |
"sep_token": "[SEP]",
|
| 16 |
+
"stride": 0,
|
| 17 |
"strip_accents": null,
|
| 18 |
"tokenize_chinese_chars": false,
|
| 19 |
"tokenizer_class": "ElectraTokenizer",
|
| 20 |
+
"truncation_side": "right",
|
| 21 |
+
"truncation_strategy": "longest_first",
|
| 22 |
"unk_token": "[UNK]"
|
| 23 |
}
|