Chintan-Shah commited on
Commit
7efe32b
·
verified ·
1 Parent(s): 9828939

Updated merges and vocab with 10000 vocab size and merging the 3 byte char tokens for devnagari script first

Browse files
Files changed (2) hide show
  1. merges.pkl +2 -2
  2. vocab.pkl +2 -2
merges.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:850574127a29f8897d385b1db670098ffd30d8dd45647b2a86c83589793012dd
3
- size 51268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0217f34adf58ef250e72b57a11a7bfe7b56eea397978c160fb86ef0b1ac90dfc
3
+ size 105610
vocab.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1809793f104622a8b69b903ee2533985ef126e9150277fec0db438470980aeca
3
- size 82534
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b471fb6500e5b3aa469c5c0e85516adf0012ceae8ebe1d1ef0c81c95db8ab8
3
+ size 178804