hoangton commited on
Commit
8f95472
1 Parent(s): 2be7a4f

Upload 2 files

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. tokenizer.json +3 -0
  3. tokenizer_config.json +11 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  phogpt-7b5.gguf 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
  phogpt-7b5.gguf filter=lfs diff=lfs merge=lfs -text
37
+ 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 sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
3
+ size 14500471
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 2048,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "right",
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }