Samba commited on
Commit
cc1e284
1 Parent(s): 0a0c569

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +13 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +10 -0
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "bos_token": "<|endoftext|>",
10
+ "eos_token": "<|endoftext|>",
11
+ "pad_token": "<|endoftext|>",
12
+ "unk_token": "<|endoftext|>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<|endoftext|>",
8
+ "tokenizer_class": "GPTNeoXTokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }