asmaslah commited on
Commit
7b47029
·
verified ·
1 Parent(s): 3c2a5a8

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 1024,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_10": 10,
30
+ "LABEL_2": 2,
31
+ "LABEL_3": 3,
32
+ "LABEL_4": 4,
33
+ "LABEL_5": 5,
34
+ "LABEL_6": 6,
35
+ "LABEL_7": 7,
36
+ "LABEL_8": 8,
37
+ "LABEL_9": 9
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "max_position_embeddings": 40000,
41
+ "model_type": "bert",
42
+ "num_attention_heads": 16,
43
+ "num_hidden_layers": 30,
44
+ "pad_token_id": 0,
45
+ "position_embedding_type": "absolute",
46
+ "transformers_version": "4.57.3",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30
50
+ }
label_encoder.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e204684e313d046764799d6f3760c99e1dd2e28ae1d44f5affb565c4595202f
3
+ size 649
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b318e49364248cbc748acbf27bd29e97cf33a0fda4c7e6ebc56198771491bdef
3
+ size 1679828396
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1000,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 0,
14
+ "pad_type_id": 0,
15
+ "pad_token": "[PAD]"
16
+ },
17
+ "added_tokens": [
18
+ {
19
+ "id": 0,
20
+ "content": "[PAD]",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "special": true
26
+ },
27
+ {
28
+ "id": 1,
29
+ "content": "[UNK]",
30
+ "single_word": false,
31
+ "lstrip": false,
32
+ "rstrip": false,
33
+ "normalized": false,
34
+ "special": true
35
+ },
36
+ {
37
+ "id": 2,
38
+ "content": "[CLS]",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": false,
43
+ "special": true
44
+ },
45
+ {
46
+ "id": 3,
47
+ "content": "[SEP]",
48
+ "single_word": false,
49
+ "lstrip": false,
50
+ "rstrip": false,
51
+ "normalized": false,
52
+ "special": true
53
+ },
54
+ {
55
+ "id": 4,
56
+ "content": "[MASK]",
57
+ "single_word": false,
58
+ "lstrip": false,
59
+ "rstrip": false,
60
+ "normalized": false,
61
+ "special": true
62
+ }
63
+ ],
64
+ "normalizer": {
65
+ "type": "BertNormalizer",
66
+ "clean_text": true,
67
+ "handle_chinese_chars": true,
68
+ "strip_accents": null,
69
+ "lowercase": false
70
+ },
71
+ "pre_tokenizer": {
72
+ "type": "BertPreTokenizer"
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "[CLS]",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ },
89
+ {
90
+ "SpecialToken": {
91
+ "id": "[SEP]",
92
+ "type_id": 0
93
+ }
94
+ }
95
+ ],
96
+ "pair": [
97
+ {
98
+ "SpecialToken": {
99
+ "id": "[CLS]",
100
+ "type_id": 0
101
+ }
102
+ },
103
+ {
104
+ "Sequence": {
105
+ "id": "A",
106
+ "type_id": 0
107
+ }
108
+ },
109
+ {
110
+ "SpecialToken": {
111
+ "id": "[SEP]",
112
+ "type_id": 0
113
+ }
114
+ },
115
+ {
116
+ "Sequence": {
117
+ "id": "B",
118
+ "type_id": 1
119
+ }
120
+ },
121
+ {
122
+ "SpecialToken": {
123
+ "id": "[SEP]",
124
+ "type_id": 1
125
+ }
126
+ }
127
+ ],
128
+ "special_tokens": {
129
+ "[CLS]": {
130
+ "id": "[CLS]",
131
+ "ids": [
132
+ 2
133
+ ],
134
+ "tokens": [
135
+ "[CLS]"
136
+ ]
137
+ },
138
+ "[SEP]": {
139
+ "id": "[SEP]",
140
+ "ids": [
141
+ 3
142
+ ],
143
+ "tokens": [
144
+ "[SEP]"
145
+ ]
146
+ }
147
+ }
148
+ },
149
+ "decoder": {
150
+ "type": "WordPiece",
151
+ "prefix": "##",
152
+ "cleanup": true
153
+ },
154
+ "model": {
155
+ "type": "WordPiece",
156
+ "unk_token": "[UNK]",
157
+ "continuing_subword_prefix": "##",
158
+ "max_input_chars_per_word": 100,
159
+ "vocab": {
160
+ "[PAD]": 0,
161
+ "[UNK]": 1,
162
+ "[CLS]": 2,
163
+ "[SEP]": 3,
164
+ "[MASK]": 4,
165
+ "L": 5,
166
+ "A": 6,
167
+ "G": 7,
168
+ "V": 8,
169
+ "E": 9,
170
+ "S": 10,
171
+ "I": 11,
172
+ "K": 12,
173
+ "R": 13,
174
+ "D": 14,
175
+ "T": 15,
176
+ "P": 16,
177
+ "N": 17,
178
+ "Q": 18,
179
+ "F": 19,
180
+ "Y": 20,
181
+ "M": 21,
182
+ "H": 22,
183
+ "C": 23,
184
+ "W": 24,
185
+ "X": 25,
186
+ "U": 26,
187
+ "B": 27,
188
+ "Z": 28,
189
+ "O": 29
190
+ }
191
+ }
192
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
vocab.txt ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD]
2
+ [UNK]
3
+ [CLS]
4
+ [SEP]
5
+ [MASK]
6
+ L
7
+ A
8
+ G
9
+ V
10
+ E
11
+ S
12
+ I
13
+ K
14
+ R
15
+ D
16
+ T
17
+ P
18
+ N
19
+ Q
20
+ F
21
+ Y
22
+ M
23
+ H
24
+ C
25
+ W
26
+ X
27
+ U
28
+ B
29
+ Z
30
+ O