Hugging Face's logo

shradha01
/
model-DeepCC-01

PyTorch
bart
Model card Files
xet
Community
1
shradha01 commited on
Commit
dcbba23
·
verified ·
1 Parent(s): 8497247

Upload of BART model with generated tokenizer

Browse files
Files changed (14) hide show
  1. .gitattributes +2 -0
  2. ast/ast.pk +0 -0
  3. ast/ast_mapping.txt +66 -0
  4. ast/ast_tokenizer.json +154 -0
  5. code/code.pk +3 -0
  6. code/code_mapping.txt +0 -0
  7. code/code_tokenizer.json +0 -0
  8. config.json +45 -0
  9. generation_config.json +11 -0
  10. nl/nl.pk +3 -0
  11. nl/nl_mapping.txt +0 -0
  12. nl/nl_tokenizer.json +0 -0
  13. pytorch_model.bin +3 -0
  14. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ code/code.pk filter=lfs diff=lfs merge=lfs -text
37
+ nl/nl.pk filter=lfs diff=lfs merge=lfs -text
ast/ast.pk ADDED
Binary file (2.89 kB). View file
 
ast/ast_mapping.txt ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD] 0
2
+ [SOS] 1
3
+ [EOS] 2
4
+ [UNK] 3
5
+ [MSK] 4
6
+ [SEP] 5
7
+ MethodInv 6
8
+ ExprStmt 7
9
+ InfixExpr 8
10
+ SingleVarDecl 9
11
+ VarDeclFrag 10
12
+ VarDeclStmt 11
13
+ IfStmt 12
14
+ ReturnStmt 13
15
+ MethodDecl 14
16
+ Asgn 15
17
+ ClassInstCreat 16
18
+ ParenthesizedExpr 17
19
+ PrefixExpr 18
20
+ CastExpr 19
21
+ ThrowStmt 20
22
+ TryStmt 21
23
+ CatchClus 22
24
+ EnhancedForStmt 23
25
+ PostfixExpr 24
26
+ ForStmt 25
27
+ BrkStmt 26
28
+ CondnExpr 27
29
+ ArrayCret 28
30
+ InstofExpr 29
31
+ WhileStmt 30
32
+ LambdaExpr 31
33
+ AnonClassDeclMethodDecl 32
34
+ ContStmt 33
35
+ SwitchStmt 34
36
+ SynchronizedStmt 35
37
+ AssertStmt 36
38
+ MethodInvMethodDecl 37
39
+ DoStmt 38
40
+ AnonClassDecl 39
41
+ ReturnStmtMethodDecl 40
42
+ FieldDecl 41
43
+ VarDeclFragMethodDecl 42
44
+ EmptyStmt 43
45
+ LabeledStmt 44
46
+ SingleVarDeclMethodDecl 45
47
+ ClassInstCreatMethodDecl 46
48
+ InfixExprMethodDecl 47
49
+ AsgnMethodDecl 48
50
+ PrefixExprMethodDecl 49
51
+ CastExprMethodDecl 50
52
+ ArrayCretMethodDecl 51
53
+ PostfixExprMethodDecl 52
54
+ ExprStmtMethodDecl 53
55
+ AnonClassDeclMethodDeclMethodDecl 54
56
+ MethodInvMethodDeclMethodDecl 55
57
+ ReturnStmtMethodDeclMethodDecl 56
58
+ ThrowStmtMethodDecl 57
59
+ ClassInstCreatMethodDeclMethodDecl 58
60
+ MethodDeclMethodDecl 59
61
+ SingleVarDeclMethodDeclMethodDecl 60
62
+ AnonClassDeclMethodDeclMethodDeclMethodDeclMethodDeclMethodDecl 61
63
+ BrkStmtMethodDecl 62
64
+ ClassInstCreatMethodDeclMethodDeclMethodDecl 63
65
+ ReturnStmtMethodDeclMethodDeclMethodDecl 64
66
+ SingleVarDeclMethodDeclMethodDeclMethodDecl 65
ast/ast_tokenizer.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[SOS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[EOS]",
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
+ "id": 4,
44
+ "content": "[MSK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "[SEP]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ }
60
+ ],
61
+ "normalizer": {
62
+ "type": "Sequence",
63
+ "normalizers": [
64
+ {
65
+ "type": "NFD"
66
+ },
67
+ {
68
+ "type": "StripAccents"
69
+ },
70
+ {
71
+ "type": "Strip",
72
+ "strip_left": true,
73
+ "strip_right": true
74
+ }
75
+ ]
76
+ },
77
+ "pre_tokenizer": {
78
+ "type": "Whitespace"
79
+ },
80
+ "post_processor": null,
81
+ "decoder": null,
82
+ "model": {
83
+ "type": "WordLevel",
84
+ "vocab": {
85
+ "[PAD]": 0,
86
+ "[SOS]": 1,
87
+ "[EOS]": 2,
88
+ "[UNK]": 3,
89
+ "[MSK]": 4,
90
+ "[SEP]": 5,
91
+ "MethodInv": 6,
92
+ "ExprStmt": 7,
93
+ "InfixExpr": 8,
94
+ "SingleVarDecl": 9,
95
+ "VarDeclFrag": 10,
96
+ "VarDeclStmt": 11,
97
+ "IfStmt": 12,
98
+ "ReturnStmt": 13,
99
+ "MethodDecl": 14,
100
+ "Asgn": 15,
101
+ "ClassInstCreat": 16,
102
+ "ParenthesizedExpr": 17,
103
+ "PrefixExpr": 18,
104
+ "CastExpr": 19,
105
+ "ThrowStmt": 20,
106
+ "TryStmt": 21,
107
+ "CatchClus": 22,
108
+ "EnhancedForStmt": 23,
109
+ "PostfixExpr": 24,
110
+ "ForStmt": 25,
111
+ "BrkStmt": 26,
112
+ "CondnExpr": 27,
113
+ "ArrayCret": 28,
114
+ "InstofExpr": 29,
115
+ "WhileStmt": 30,
116
+ "LambdaExpr": 31,
117
+ "AnonClassDeclMethodDecl": 32,
118
+ "ContStmt": 33,
119
+ "SwitchStmt": 34,
120
+ "SynchronizedStmt": 35,
121
+ "AssertStmt": 36,
122
+ "MethodInvMethodDecl": 37,
123
+ "DoStmt": 38,
124
+ "AnonClassDecl": 39,
125
+ "ReturnStmtMethodDecl": 40,
126
+ "FieldDecl": 41,
127
+ "VarDeclFragMethodDecl": 42,
128
+ "EmptyStmt": 43,
129
+ "LabeledStmt": 44,
130
+ "SingleVarDeclMethodDecl": 45,
131
+ "ClassInstCreatMethodDecl": 46,
132
+ "InfixExprMethodDecl": 47,
133
+ "AsgnMethodDecl": 48,
134
+ "PrefixExprMethodDecl": 49,
135
+ "CastExprMethodDecl": 50,
136
+ "ArrayCretMethodDecl": 51,
137
+ "PostfixExprMethodDecl": 52,
138
+ "ExprStmtMethodDecl": 53,
139
+ "AnonClassDeclMethodDeclMethodDecl": 54,
140
+ "MethodInvMethodDeclMethodDecl": 55,
141
+ "ReturnStmtMethodDeclMethodDecl": 56,
142
+ "ThrowStmtMethodDecl": 57,
143
+ "ClassInstCreatMethodDeclMethodDecl": 58,
144
+ "MethodDeclMethodDecl": 59,
145
+ "SingleVarDeclMethodDeclMethodDecl": 60,
146
+ "AnonClassDeclMethodDeclMethodDeclMethodDeclMethodDeclMethodDecl": 61,
147
+ "BrkStmtMethodDecl": 62,
148
+ "ClassInstCreatMethodDeclMethodDeclMethodDecl": 63,
149
+ "ReturnStmtMethodDeclMethodDeclMethodDecl": 64,
150
+ "SingleVarDeclMethodDeclMethodDeclMethodDecl": 65
151
+ },
152
+ "unk_token": "[UNK]"
153
+ }
154
+ }
code/code.pk ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0380c45e108679eab568fb72bca1f6f5ab73307196defd0801d326a5d9a31594
3
+ size 1583869
code/code_mapping.txt ADDED
The diff for this file is too large to render. See raw diff
 
code/code_tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "BartForClassificationAndGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "classifier_dropout": 0.0,
10
+ "d_model": 768,
11
+ "decoder_attention_heads": 12,
12
+ "decoder_ffn_dim": 3072,
13
+ "decoder_layerdrop": 0.0,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 1,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 12,
18
+ "encoder_ffn_dim": 3072,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_layers": 12,
21
+ "eos_token_id": 2,
22
+ "forced_eos_token_id": 2,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "max_length": 256,
34
+ "max_position_embeddings": 1024,
35
+ "min_length": 1,
36
+ "model_type": "bart",
37
+ "num_beams": 5,
38
+ "num_hidden_layers": 12,
39
+ "pad_token_id": 0,
40
+ "scale_embedding": false,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.36.2",
43
+ "use_cache": true,
44
+ "vocab_size": 80066
45
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "max_length": 256,
7
+ "min_length": 1,
8
+ "num_beams": 5,
9
+ "pad_token_id": 0,
10
+ "transformers_version": "4.36.2"
11
+ }
nl/nl.pk ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13e20d9f3a4d3349eec7e68763acc182b9e6dbe06205d09672f26a38db4d166
3
+ size 870400
nl/nl_mapping.txt ADDED
The diff for this file is too large to render. See raw diff
 
nl/nl_tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae05d2ccba6797eeccdc23fe0c232baafa35edefbe54d189759dac57e06ab51
3
+ size 1049047002
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5150f7ffb6e649f15cd09c2d6a029de299bd82a75ee2b71ef42fd2a133402169
3
+ size 4920