Hugging Face's logo

ardauzunoglu
/
mod_tokenizer

Model card Files
xet
 Community
ardauzunoglu commited on
Commit
a32d454
·
verified ·
1 Parent(s): a0cab05

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +6 -0
  2. token_mapping.txt +18 -0
  3. tokenizer.json +72 -0
  4. tokenizer_config.json +44 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
token_mapping.txt ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Token ID
2
+ <pad> 0
3
+ <s> 1
4
+ </s> 2
5
+ <unk> 3
6
+ 0 4
7
+ 1 5
8
+ 2 6
9
+ 3 7
10
+ 4 8
11
+ 5 9
12
+ 6 10
13
+ 7 11
14
+ 8 12
15
+ 9 13
16
+ MOD_10 14
17
+ EQUALS 15
18
+ END 16
tokenizer.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<pad>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Whitespace"
46
+ },
47
+ "post_processor": null,
48
+ "decoder": null,
49
+ "model": {
50
+ "type": "WordLevel",
51
+ "vocab": {
52
+ "<pad>": 0,
53
+ "<s>": 1,
54
+ "</s>": 2,
55
+ "<unk>": 3,
56
+ "0": 4,
57
+ "1": 5,
58
+ "2": 6,
59
+ "3": 7,
60
+ "4": 8,
61
+ "5": 9,
62
+ "6": 10,
63
+ "7": 11,
64
+ "8": 12,
65
+ "9": 13,
66
+ "MOD_10": 14,
67
+ "EQUALS": 15,
68
+ "END": 16
69
+ },
70
+ "unk_token": "<unk>"
71
+ }
72
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "extra_special_tokens": {},
40
+ "model_max_length": 512,
41
+ "pad_token": "<pad>",
42
+ "tokenizer_class": "PreTrainedTokenizerFast",
43
+ "unk_token": "<unk>"
44
+ }