sileod commited on
Commit
ae80b39
1 Parent(s): 8fecc7c

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer.json +6 -4
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 256
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
@@ -90,7 +90,8 @@
90
  {
91
  "type": "Metaspace",
92
  "replacement": "▁",
93
- "add_prefix_space": true
 
94
  }
95
  ]
96
  },
@@ -172,7 +173,8 @@
172
  "decoder": {
173
  "type": "Metaspace",
174
  "replacement": "▁",
175
- "add_prefix_space": true
 
176
  },
177
  "model": {
178
  "type": "Unigram",
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 1680,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 1680
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
90
  {
91
  "type": "Metaspace",
92
  "replacement": "▁",
93
+ "prepend_scheme": "always",
94
+ "split": true
95
  }
96
  ]
97
  },
 
173
  "decoder": {
174
  "type": "Metaspace",
175
  "replacement": "▁",
176
+ "prepend_scheme": "always",
177
+ "split": true
178
  },
179
  "model": {
180
  "type": "Unigram",