GuillemGSubies commited on
Commit
ceaa931
1 Parent(s): a62f67c

Upload the tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +18 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "keep_accents": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_len": 512,
8
+ "model_max_length": 512,
9
+ "name_or_path": "models/BETO_Galen-16-3e-05-0.1-cantemist_best",
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "/home/guillem.garcia/.cache/huggingface/hub/models--dccuchile--bert-base-spanish-wwm-cased/snapshots/56a7647b957a4230fc3f80dafbe80f2ba9b0de73/special_tokens_map.json",
14
+ "strip_accents": false,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "BertTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff