updated tokenizer
Browse files- tokenizer.json +16 -2
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
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": 64,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 64
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 1,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "</s>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -931,7 +931,7 @@
|
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
"legacy": false,
|
934 |
-
"model_max_length":
|
935 |
"pad_token": "</s>",
|
936 |
"sp_model_kwargs": {},
|
937 |
"tokenizer_class": "T5Tokenizer",
|
|
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
"legacy": false,
|
934 |
+
"model_max_length": 64,
|
935 |
"pad_token": "</s>",
|
936 |
"sp_model_kwargs": {},
|
937 |
"tokenizer_class": "T5Tokenizer",
|