fix tokenizer
Browse files- tokenizer.json +3 -17
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 256,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 256
|
| 12 |
-
},
|
| 13 |
-
"direction": "Left",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 128009,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<|eot_id|>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 128000,
|
|
@@ -410574,4 +410560,4 @@
|
|
| 410574 |
"éĶ ¦"
|
| 410575 |
]
|
| 410576 |
}
|
| 410577 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 128000,
|
|
|
|
| 410560 |
"éĶ ¦"
|
| 410561 |
]
|
| 410562 |
}
|
| 410563 |
+
}
|