jh
Browse files- tokenizer_config.json +12 -16
tokenizer_config.json
CHANGED
@@ -1,17 +1,13 @@
|
|
1 |
-
|
2 |
-
{
|
3 |
-
"
|
4 |
-
|
5 |
-
"tokenizeConfig.OBITokenizer",
|
6 |
-
null
|
7 |
-
]
|
8 |
-
},
|
9 |
-
"bos_token": "<s>",
|
10 |
-
"clean_up_tokenization_spaces": false,
|
11 |
-
"eos_token": "</s>",
|
12 |
-
"model_max_length": 1000000000000000019884624838656,
|
13 |
-
"pad_token": "</s>",
|
14 |
"tokenizer_class": "OBITokenizer",
|
15 |
-
"
|
16 |
-
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
{
|
3 |
+
"pat_str": "'s|'t|'re|'ve|'m|'ll|'d| ?[\\p{L}]+| ?[\\p{N}]+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+",
|
4 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"tokenizer_class": "OBITokenizer",
|
6 |
+
"auto_map": {
|
7 |
+
"AutoTokenizer": [
|
8 |
+
"tokenizeConfig.OBITokenizer",
|
9 |
+
null
|
10 |
+
]
|
11 |
+
},
|
12 |
+
"vocab_size": 600
|
13 |
+
}
|