sdadas commited on
Commit
6ed976c
1 Parent(s): 045c3c1

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "model_max_length": 1536,
8
+ "name_or_path": "original/polish-gpt2-xl",
9
+ "special_tokens_map_file": "original/polish-gpt2-xl/special_tokens_map.json",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<unk>"
12
+ }