Hugging Face's logo

Sumitp
/
Text_to_SQL_BART_sumit

Text2Text Generation
Transformers
PyTorch
bart
Inference Endpoints
Model card Files Community
2
Sumitp commited on
Commit
3b424f9
•
1 Parent(s): 070887a

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +52 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +15 -0
  4. tokenizer_config.json +64 -0
  5. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<col0>": 50265,
3
+ "<col10>": 50275,
4
+ "<col11>": 50276,
5
+ "<col12>": 50277,
6
+ "<col13>": 50278,
7
+ "<col14>": 50279,
8
+ "<col15>": 50280,
9
+ "<col16>": 50281,
10
+ "<col17>": 50282,
11
+ "<col18>": 50283,
12
+ "<col19>": 50284,
13
+ "<col1>": 50266,
14
+ "<col20>": 50285,
15
+ "<col21>": 50286,
16
+ "<col22>": 50287,
17
+ "<col23>": 50288,
18
+ "<col24>": 50289,
19
+ "<col25>": 50290,
20
+ "<col26>": 50291,
21
+ "<col27>": 50292,
22
+ "<col28>": 50293,
23
+ "<col29>": 50294,
24
+ "<col2>": 50267,
25
+ "<col30>": 50295,
26
+ "<col31>": 50296,
27
+ "<col32>": 50297,
28
+ "<col33>": 50298,
29
+ "<col34>": 50299,
30
+ "<col35>": 50300,
31
+ "<col36>": 50301,
32
+ "<col37>": 50302,
33
+ "<col38>": 50303,
34
+ "<col39>": 50304,
35
+ "<col3>": 50268,
36
+ "<col40>": 50305,
37
+ "<col41>": 50306,
38
+ "<col42>": 50307,
39
+ "<col43>": 50308,
40
+ "<col44>": 50309,
41
+ "<col45>": 50310,
42
+ "<col46>": 50311,
43
+ "<col47>": 50312,
44
+ "<col48>": 50313,
45
+ "<col49>": 50314,
46
+ "<col4>": 50269,
47
+ "<col5>": 50270,
48
+ "<col6>": 50271,
49
+ "<col7>": 50272,
50
+ "<col8>": 50273,
51
+ "<col9>": 50274
52
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 1024,
37
+ "name_or_path": "shahrukhx01/schema-aware-denoising-bart-large-cnn-text2sql",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "BartTokenizer",
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff