Spanish
sapinedamo commited on
Commit
2ac1b3b
1 Parent(s): 9922195

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "<s>",
5
+ "</s>",
6
+ "<unk>",
7
+ "[PAD]"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "eos_token": "</s>",
11
+ "pad_token": "[PAD]",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9051199beacf71b5afaf6058198951c587ac0d6702f3871b122d8bf5660d72b7
3
+ size 14501256
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "max_length": 512,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "BloomTokenizer",
11
+ "unk_token": "<unk>"
12
+ }