VictorMorand commited on
Commit
ee3ab86
·
verified ·
1 Parent(s): 408be9d

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +23 -0
config.json CHANGED
@@ -38,7 +38,7 @@
38
  "relative_attention": true,
39
  "share_att_key": true,
40
  "tie_word_embeddings": true,
41
- "transformers_version": "5.0.0",
42
  "type_vocab_size": 0,
43
  "vocab_size": 128100
44
  }
 
38
  "relative_attention": true,
39
  "share_att_key": true,
40
  "tie_word_embeddings": true,
41
+ "transformers_version": "5.3.0",
42
  "type_vocab_size": 0,
43
  "vocab_size": 128100
44
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "split_by_punct": false,
19
+ "tokenizer_class": "DebertaV2Tokenizer",
20
+ "unk_id": 3,
21
+ "unk_token": "[UNK]",
22
+ "vocab_type": "spm"
23
+ }