Ketak-ZoomRx commited on
Commit
c13bb8b
1 Parent(s): 201c30f

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "cls_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "pad_token": "<|endoftext|>",
6
+ "sep_token": "<|endoftext|>",
7
+ "unk_token": "<|endoftext|>"
8
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }