Hugging Face's logo

keriii
/
KerodAmharicToekenizer

Model card Files Community
2

Update tokenizer_config.json

#2
by AbelBekele - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+32
-55
Files changed (1) hide show
  1. tokenizer_config.json +32 -55
tokenizer_config.json CHANGED
@@ -1,58 +1,35 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": true,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
  },
44
- "bos_token": "[CLS]",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "do_lower_case": false,
48
- "eos_token": "[SEP]",
49
- "mask_token": "[MASK]",
50
- "max_len": 512,
51
- "model_max_length": 512,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
 
 
 
54
  "sp_model_kwargs": {},
55
- "split_by_punct": false,
56
- "tokenizer_class": "DebertaV2Tokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
 
 
 
 
 
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
  "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }