santoshsto commited on
Commit
ada7683
·
verified ·
1 Parent(s): 5b3c66c

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -17
  2. tokenizer.model +3 -0
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": "Left",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 2,
16
- "pad_type_id": 0,
17
- "pad_token": "</s>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
@@ -175,7 +161,6 @@
175
  "end_of_word_suffix": null,
176
  "fuse_unk": true,
177
  "byte_fallback": true,
178
- "ignore_merges": false,
179
  "vocab": {
180
  "<unk>": 0,
181
  "<s>": 1,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
161
  "end_of_word_suffix": null,
162
  "fuse_unk": true,
163
  "byte_fallback": true,
 
164
  "vocab": {
165
  "<unk>": 0,
166
  "<s>": 1,
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443