Upload tokenizer
Browse files- tokenizer.json +16 -2
- tokenizer_config.json +2 -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": 50,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 50
|
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
@@ -46,7 +46,7 @@
|
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"max_length":
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
51 |
"never_split": null,
|
52 |
"pad_token": "[PAD]",
|
@@ -55,5 +55,6 @@
|
|
55 |
"strip_accents": null,
|
56 |
"tokenize_chinese_chars": true,
|
57 |
"tokenizer_class": "BertTokenizer",
|
|
|
58 |
"unk_token": "[UNK]"
|
59 |
}
|
|
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
+
"max_length": 50,
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
51 |
"never_split": null,
|
52 |
"pad_token": "[PAD]",
|
|
|
55 |
"strip_accents": null,
|
56 |
"tokenize_chinese_chars": true,
|
57 |
"tokenizer_class": "BertTokenizer",
|
58 |
+
"truncation": true,
|
59 |
"unk_token": "[UNK]"
|
60 |
}
|