legacy107 commited on
Commit
c4c6647
1 Parent(s): b575640

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +9 -2
  2. tokenizer_config.json +5 -0
tokenizer.json CHANGED
@@ -2,11 +2,18 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 200,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
- "padding": null,
 
 
 
 
 
 
 
10
  "added_tokens": [
11
  {
12
  "id": 0,
 
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": null,
13
+ "pad_id": 0,
14
+ "pad_type_id": 0,
15
+ "pad_token": "<pad>"
16
+ },
17
  "added_tokens": [
18
  {
19
  "id": 0,
tokenizer_config.json CHANGED
@@ -102,11 +102,16 @@
102
  "<extra_id_99>"
103
  ],
104
  "clean_up_tokenization_spaces": true,
 
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
 
107
  "model_max_length": 512,
108
  "pad_token": "<pad>",
109
  "sp_model_kwargs": {},
 
110
  "tokenizer_class": "T5Tokenizer",
 
 
111
  "unk_token": "<unk>"
112
  }
 
102
  "<extra_id_99>"
103
  ],
104
  "clean_up_tokenization_spaces": true,
105
+ "device_map": "auto",
106
  "eos_token": "</s>",
107
  "extra_ids": 100,
108
+ "max_length": 200,
109
  "model_max_length": 512,
110
  "pad_token": "<pad>",
111
  "sp_model_kwargs": {},
112
+ "stride": 0,
113
  "tokenizer_class": "T5Tokenizer",
114
+ "truncation_side": "right",
115
+ "truncation_strategy": "longest_first",
116
  "unk_token": "<unk>"
117
  }