loubnabnl HF staff commited on
Commit
694db92
1 Parent(s): 106635d

Upload tokenizer

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>"
4
+ ],
5
+ "bos_token": "<|endoftext|>",
6
+ "eos_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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "additional_special_tokens": [
4
+ "<|endoftext|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "clean_up_tokenization_spaces": true,
8
+ "eos_token": "<|endoftext|>",
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>",
12
+ "vocab_size": 49152
13
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff