Hugging Face's logo

ishaansharma
/
topic-detector

Text Classification
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
2
ishaansharma commited on
Commit
4ee785d
•
1 Parent(s): bdcfd85

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +71 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +64 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/tweet-topic-21-multi",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "arts_&_culture",
16
+ "1": "business_&_entrepreneurs",
17
+ "2": "celebrity_&_pop_culture",
18
+ "3": "diaries_&_daily_life",
19
+ "4": "family",
20
+ "5": "fashion_&_style",
21
+ "6": "film_tv_&_video",
22
+ "7": "fitness_&_health",
23
+ "8": "food_&_dining",
24
+ "9": "gaming",
25
+ "10": "learning_&_educational",
26
+ "11": "music",
27
+ "12": "news_&_social_concern",
28
+ "13": "other_hobbies",
29
+ "14": "relationships",
30
+ "15": "science_&_technology",
31
+ "16": "sports",
32
+ "17": "travel_&_adventure",
33
+ "18": "youth_&_student_life"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "arts_&_culture": 0,
39
+ "business_&_entrepreneurs": 1,
40
+ "celebrity_&_pop_culture": 2,
41
+ "diaries_&_daily_life": 3,
42
+ "family": 4,
43
+ "fashion_&_style": 5,
44
+ "film_tv_&_video": 6,
45
+ "fitness_&_health": 7,
46
+ "food_&_dining": 8,
47
+ "gaming": 9,
48
+ "learning_&_educational": 10,
49
+ "music": 11,
50
+ "news_&_social_concern": 12,
51
+ "other_hobbies": 13,
52
+ "relationships": 14,
53
+ "science_&_technology": 15,
54
+ "sports": 16,
55
+ "travel_&_adventure": 17,
56
+ "youth_&_student_life": 18
57
+ },
58
+ "layer_norm_eps": 1e-05,
59
+ "max_position_embeddings": 514,
60
+ "model_type": "roberta",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 1,
64
+ "position_embedding_type": "absolute",
65
+ "problem_type": "multi_label_classification",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.21.2",
68
+ "type_vocab_size": 1,
69
+ "use_cache": true,
70
+ "vocab_size": 50265
71
+ }
merges.txt 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:f12f0634ac3d5b6758a487ad0bb0caac10f76cba72c7a5677c747b1ab960c0b8
3
+ size 498711541
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ "name_or_path": "cardiffnlp/tweet-topic-21-multi",
37
+ "pad_token": {
38
+ "__type": "AddedToken",
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "__type": "AddedToken",
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "special_tokens_map_file": "/home/antypasd/.cache/huggingface/transformers/601312a9cb96656475ff2ef71b3b002f803e0889279718ab471aed2c84b95b18.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
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