amgadhasan commited on
Commit
97021c8
1 Parent(s): cb720f8

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ }
11
+ },
12
+ "bos_token": "<|endoftext|>",
13
+ "clean_up_tokenization_spaces": true,
14
+ "eos_token": "<|endoftext|>",
15
+ "model_max_length": 8192,
16
+ "pad_token": "<|endoftext|>",
17
+ "tokenizer_class": "PreTrainedTokenizerFast",
18
+ "unk_token": "<|endoftext|>"
19
+ }