Commit ·
77655aa
1
Parent(s): f127f73
Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +14 -2
special_tokens_map.json
CHANGED
|
@@ -102,6 +102,6 @@
|
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
"eos_token": "</s>",
|
| 105 |
-
"pad_token": "<
|
| 106 |
"unk_token": "<unk>"
|
| 107 |
}
|
|
|
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "</s>",
|
| 106 |
"unk_token": "<unk>"
|
| 107 |
}
|
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": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": "BatchLongest",
|
| 11 |
+
"direction": "Right",
|
| 12 |
+
"pad_to_multiple_of": null,
|
| 13 |
+
"pad_id": 1,
|
| 14 |
+
"pad_type_id": 0,
|
| 15 |
+
"pad_token": "</s>"
|
| 16 |
+
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|