Edgar404 commited on
Commit
9189d1c
·
verified ·
1 Parent(s): 7408bea

Upload processor

Browse files
Files changed (1) hide show
  1. tokenizer.json +6 -20
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 1,
16
- "pad_type_id": 0,
17
- "pad_token": "<pad>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
@@ -213,8 +199,8 @@
213
  "pre_tokenizer": {
214
  "type": "Metaspace",
215
  "replacement": "▁",
216
- "prepend_scheme": "always",
217
- "split": true
218
  },
219
  "post_processor": {
220
  "type": "TemplateProcessing",
@@ -300,8 +286,8 @@
300
  "decoder": {
301
  "type": "Metaspace",
302
  "replacement": "▁",
303
- "prepend_scheme": "always",
304
- "split": true
305
  },
306
  "model": {
307
  "type": "Unigram",
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
199
  "pre_tokenizer": {
200
  "type": "Metaspace",
201
  "replacement": "▁",
202
+ "add_prefix_space": true,
203
+ "prepend_scheme": "always"
204
  },
205
  "post_processor": {
206
  "type": "TemplateProcessing",
 
286
  "decoder": {
287
  "type": "Metaspace",
288
  "replacement": "▁",
289
+ "add_prefix_space": true,
290
+ "prepend_scheme": "always"
291
  },
292
  "model": {
293
  "type": "Unigram",