Upload tokenizer
Browse files- tokenizer.json +11 -2
- tokenizer_config.json +4 -1
tokenizer.json
CHANGED
|
@@ -2,11 +2,20 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
| 12 |
"id": 0,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 128
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -46,9 +46,12 @@
|
|
| 46 |
"do_lower_case": true,
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
-
"max_length":
|
| 50 |
"model_max_length": 512,
|
|
|
|
| 51 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"stride": 0,
|
| 54 |
"strip_accents": null,
|
|
|
|
| 46 |
"do_lower_case": true,
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 128,
|
| 50 |
"model_max_length": 512,
|
| 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,
|