finiteautomata commited on
Commit
bed28c6
1 Parent(s): 61d4bd1

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64004
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "max_len": 128,
7
+ "model_max_length": 128,
8
+ "name_or_path": "melll-uff/bertweetbr",
9
+ "normalization": false,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": "C:\\Users\\y435\\.cache\\huggingface\\transformers\\d3ac3efbfcf6ec1d20748abc90e96ca8452f1fc27cdbf11c887a5bbf50c26cd6.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8",
13
+ "tokenizer_class": "BertweetTokenizer",
14
+ "tokenizer_file": null,
15
+ "unk_token": "<unk>"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff