Hugging Face's logo

Petercusin
/
English-news-category-classifier

Text Classification
Safetensors
English
distilbert
code
Model card Files
xet
 Community
Petercusin commited on
Commit
0e051a4
·
verified ·
1 Parent(s): 992d4fe

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +113 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer_config.json +57 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "D:\\Software\\bert\\distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LATINO VOICES",
13
+ "1": "ARTS",
14
+ "2": "CULTURE & ARTS",
15
+ "3": "HOME & LIVING",
16
+ "4": "ARTS & CULTURE",
17
+ "5": "THE WORLDPOST",
18
+ "6": "GOOD NEWS",
19
+ "7": "FIFTY",
20
+ "8": "CRIME",
21
+ "9": "RELIGION",
22
+ "10": "PARENTS",
23
+ "11": "TASTE",
24
+ "12": "WORLDPOST",
25
+ "13": "WORLD NEWS",
26
+ "14": "EDUCATION",
27
+ "15": "QUEER VOICES",
28
+ "16": "PARENTING",
29
+ "17": "MONEY",
30
+ "18": "SPORTS",
31
+ "19": "POLITICS",
32
+ "20": "WELLNESS",
33
+ "21": "GREEN",
34
+ "22": "BUSINESS",
35
+ "23": "TECH",
36
+ "24": "ENVIRONMENT",
37
+ "25": "WOMEN",
38
+ "26": "U.S. NEWS",
39
+ "27": "HEALTHY LIVING",
40
+ "28": "DIVORCE",
41
+ "29": "MEDIA",
42
+ "30": "ENTERTAINMENT",
43
+ "31": "WEDDINGS",
44
+ "32": "BLACK VOICES",
45
+ "33": "STYLE",
46
+ "34": "IMPACT",
47
+ "35": "WEIRD NEWS",
48
+ "36": "FOOD & DRINK",
49
+ "37": "TRAVEL",
50
+ "38": "COLLEGE",
51
+ "39": "SCIENCE",
52
+ "40": "STYLE & BEAUTY",
53
+ "41": "COMEDY"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "label2id": {
57
+ "ARTS": 1,
58
+ "ARTS & CULTURE": 4,
59
+ "BLACK VOICES": 32,
60
+ "BUSINESS": 22,
61
+ "COLLEGE": 38,
62
+ "COMEDY": 41,
63
+ "CRIME": 8,
64
+ "CULTURE & ARTS": 2,
65
+ "DIVORCE": 28,
66
+ "EDUCATION": 14,
67
+ "ENTERTAINMENT": 30,
68
+ "ENVIRONMENT": 24,
69
+ "FIFTY": 7,
70
+ "FOOD & DRINK": 36,
71
+ "GOOD NEWS": 6,
72
+ "GREEN": 21,
73
+ "HEALTHY LIVING": 27,
74
+ "HOME & LIVING": 3,
75
+ "IMPACT": 34,
76
+ "LATINO VOICES": 0,
77
+ "MEDIA": 29,
78
+ "MONEY": 17,
79
+ "PARENTING": 16,
80
+ "PARENTS": 10,
81
+ "POLITICS": 19,
82
+ "QUEER VOICES": 15,
83
+ "RELIGION": 9,
84
+ "SCIENCE": 39,
85
+ "SPORTS": 18,
86
+ "STYLE": 33,
87
+ "STYLE & BEAUTY": 40,
88
+ "TASTE": 11,
89
+ "TECH": 23,
90
+ "THE WORLDPOST": 5,
91
+ "TRAVEL": 37,
92
+ "U.S. NEWS": 26,
93
+ "WEDDINGS": 31,
94
+ "WEIRD NEWS": 35,
95
+ "WELLNESS": 20,
96
+ "WOMEN": 25,
97
+ "WORLD NEWS": 13,
98
+ "WORLDPOST": 12
99
+ },
100
+ "max_position_embeddings": 512,
101
+ "model_type": "distilbert",
102
+ "n_heads": 12,
103
+ "n_layers": 6,
104
+ "pad_token_id": 0,
105
+ "problem_type": "single_label_classification",
106
+ "qa_dropout": 0.1,
107
+ "seq_classif_dropout": 0.2,
108
+ "sinusoidal_pos_embds": false,
109
+ "tie_weights_": true,
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.46.3",
112
+ "vocab_size": 30522
113
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffdfbd845cb23bf152f1167947df0674154d273ef849b4e89b552d6b749db3b3
3
+ size 267955616
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_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff