NorbertRop commited on
Commit
99838ce
1 Parent(s): 94b54db

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
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "</s>",
7
+ "unk_token": "<unk>"
8
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "do_lowercase_and_remove_accent": false,
6
+ "id2lang": null,
7
+ "lang2id": null,
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "name_or_path": "allegro/herbert-base-cased",
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "special_tokens_map_file": "/data5/nropiak/.cache/huggingface/hub/models--allegro--herbert-base-cased/snapshots/50e33e0567be0c0b313832314c586e3df0dc2297/special_tokens_map.json",
14
+ "tokenizer_class": "HerbertTokenizer",
15
+ "unk_token": "<unk>"
16
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff