chetan phakami pun commited on
Commit
f103455
1 Parent(s): 5aec84f

Added multilingual BPE tokenizer

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. tokenizer.json +3 -0
  3. tokenizer_config.json +1 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be0fcba55321c24fc99e48ea4d544b138e1264e78cd66b6cfe2466f6ebc2fe1
3
+ size 1470734
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_type": "bpe", "special_tokens": {"pad_token": "<pad>", "unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}, "vocab_size": 32000}