Hezar: Upload model and config
Browse files- preprocessor/tokenizer.json +16 -3
preprocessor/tokenizer.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -129033,6 +129045,7 @@
|
|
| 129033 |
"ゑ",
|
| 129034 |
-23.117965246724
|
| 129035 |
]
|
| 129036 |
-
]
|
|
|
|
| 129037 |
}
|
| 129038 |
}
|
|
|
|
| 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": 0,
|
| 13 |
+
"pad_id": 0,
|
| 14 |
+
"pad_type_id": 0,
|
| 15 |
+
"pad_token": "<pad>"
|
| 16 |
+
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 129045 |
"ゑ",
|
| 129046 |
-23.117965246724
|
| 129047 |
]
|
| 129048 |
+
],
|
| 129049 |
+
"byte_fallback": false
|
| 129050 |
}
|
| 129051 |
}
|