Hugging Face's logo

logasanjeev
/
goemotions-bert

Text Classification
Safetensors
English
bert
multi-label
go_emotions
emotion-classification
Model card Files
xet
Community
logasanjeev commited on
Commit
6de6427
·
verified ·
1 Parent(s): 0ad9e81

Upload fine-tuned BERT-base for GoEmotions with optimized thresholds

Browse files
Files changed (6) hide show
  1. config.json +86 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +7 -0
  4. thresholds.json +62 -0
  5. tokenizer_config.json +58 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
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
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_10": 10,
47
+ "LABEL_11": 11,
48
+ "LABEL_12": 12,
49
+ "LABEL_13": 13,
50
+ "LABEL_14": 14,
51
+ "LABEL_15": 15,
52
+ "LABEL_16": 16,
53
+ "LABEL_17": 17,
54
+ "LABEL_18": 18,
55
+ "LABEL_19": 19,
56
+ "LABEL_2": 2,
57
+ "LABEL_20": 20,
58
+ "LABEL_21": 21,
59
+ "LABEL_22": 22,
60
+ "LABEL_23": 23,
61
+ "LABEL_24": 24,
62
+ "LABEL_25": 25,
63
+ "LABEL_26": 26,
64
+ "LABEL_27": 27,
65
+ "LABEL_3": 3,
66
+ "LABEL_4": 4,
67
+ "LABEL_5": 5,
68
+ "LABEL_6": 6,
69
+ "LABEL_7": 7,
70
+ "LABEL_8": 8,
71
+ "LABEL_9": 9
72
+ },
73
+ "layer_norm_eps": 1e-12,
74
+ "max_position_embeddings": 512,
75
+ "model_type": "bert",
76
+ "num_attention_heads": 12,
77
+ "num_hidden_layers": 12,
78
+ "pad_token_id": 0,
79
+ "position_embedding_type": "absolute",
80
+ "problem_type": "multi_label_classification",
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.51.1",
83
+ "type_vocab_size": 2,
84
+ "use_cache": true,
85
+ "vocab_size": 30522
86
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491a23b02d2e5898230899e96c99d8dd828ba61258fec0406c2ecc8258db0766
3
+ size 438038624
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
+ }
thresholds.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "emotion_labels": [
3
+ "admiration",
4
+ "amusement",
5
+ "anger",
6
+ "annoyance",
7
+ "approval",
8
+ "caring",
9
+ "confusion",
10
+ "curiosity",
11
+ "desire",
12
+ "disappointment",
13
+ "disapproval",
14
+ "disgust",
15
+ "embarrassment",
16
+ "excitement",
17
+ "fear",
18
+ "gratitude",
19
+ "grief",
20
+ "joy",
21
+ "love",
22
+ "nervousness",
23
+ "optimism",
24
+ "pride",
25
+ "realization",
26
+ "relief",
27
+ "remorse",
28
+ "sadness",
29
+ "surprise",
30
+ "neutral"
31
+ ],
32
+ "thresholds": [
33
+ 0.5000000000000001,
34
+ 0.45000000000000007,
35
+ 0.45000000000000007,
36
+ 0.3500000000000001,
37
+ 0.40000000000000013,
38
+ 0.40000000000000013,
39
+ 0.45000000000000007,
40
+ 0.3500000000000001,
41
+ 0.6000000000000002,
42
+ 0.3500000000000001,
43
+ 0.40000000000000013,
44
+ 0.5000000000000001,
45
+ 0.5000000000000001,
46
+ 0.45000000000000007,
47
+ 0.3500000000000001,
48
+ 0.6000000000000002,
49
+ 0.3500000000000001,
50
+ 0.40000000000000013,
51
+ 0.5000000000000001,
52
+ 0.45000000000000007,
53
+ 0.45000000000000007,
54
+ 0.30000000000000004,
55
+ 0.5000000000000001,
56
+ 0.40000000000000013,
57
+ 0.3500000000000001,
58
+ 0.5500000000000002,
59
+ 0.40000000000000013,
60
+ 0.3500000000000001
61
+ ]
62
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff