Hugging Face's logo

TrumpMcDonaldz
/
piuba-bigdata-beto-contextualized-hate-speech-ONNX

ONNX
bert
Model card Files Community
TrumpMcDonaldz commited on
Commit
28f723b
•
1 Parent(s): dd624da

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. added_tokens.json +6 -0
  2. config.json +49 -0
  3. onnx/decoder_model_merged.onnx +3 -0
  4. onnx/decoder_model_merged_quantized.onnx +3 -0
  5. quantize_config.json +32 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +93 -0
  9. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "@usuario": 31002,
3
+ "emoji": 31005,
4
+ "hashtag": 31004,
5
+ "url": 31003
6
+ }
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "piuba-bigdata/beto-contextualized-hate-speech",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "CALLS",
14
+ "1": "WOMEN",
15
+ "2": "LGBTI",
16
+ "3": "RACISM",
17
+ "4": "CLASS",
18
+ "5": "POLITICS",
19
+ "6": "DISABLED",
20
+ "7": "APPEARANCE",
21
+ "8": "CRIMINAL"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "APPEARANCE": 7,
27
+ "CALLS": 0,
28
+ "CLASS": 4,
29
+ "CRIMINAL": 8,
30
+ "DISABLED": 6,
31
+ "LGBTI": 2,
32
+ "POLITICS": 5,
33
+ "RACISM": 3,
34
+ "WOMEN": 1
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "output_past": true,
42
+ "pad_token_id": 1,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "multi_label_classification",
45
+ "transformers_version": "4.35.2",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 31006
49
+ }
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf447c478666afd8985bc852327477d1f081de570a9df2bd79fe24c7c6fe0c04
3
+ size 439710262
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84376f39ae319a4f46f132027cfcc3ba71a8dba20381bbff9b50620c4fde6a3f
3
+ size 111094390
quantize_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Mul",
8
+ "Transpose",
9
+ "Reshape",
10
+ "Slice",
11
+ "Gemm",
12
+ "Div",
13
+ "Cast",
14
+ "MatMul",
15
+ "Gather",
16
+ "Sub",
17
+ "Constant",
18
+ "Shape",
19
+ "ReduceMean",
20
+ "Softmax",
21
+ "Tanh",
22
+ "Erf",
23
+ "Unsqueeze",
24
+ "Sqrt",
25
+ "Concat",
26
+ "Pow",
27
+ "Add"
28
+ ],
29
+ "weight_type": "QInt8"
30
+ }
31
+ }
32
+ }
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[MASK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "31002": {
44
+ "content": "@usuario",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "31003": {
52
+ "content": "url",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "31004": {
60
+ "content": "hashtag",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "31005": {
68
+ "content": "emoji",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ }
75
+ },
76
+ "clean_up_tokenization_spaces": true,
77
+ "cls_token": "[CLS]",
78
+ "do_basic_tokenize": true,
79
+ "do_lower_case": false,
80
+ "mask_token": "[MASK]",
81
+ "max_length": 256,
82
+ "model_max_length": 256,
83
+ "never_split": null,
84
+ "pad_token": "[PAD]",
85
+ "sep_token": "[SEP]",
86
+ "stride": 0,
87
+ "strip_accents": false,
88
+ "tokenize_chinese_chars": true,
89
+ "tokenizer_class": "BertTokenizer",
90
+ "truncation_side": "right",
91
+ "truncation_strategy": "longest_first",
92
+ "unk_token": "[UNK]"
93
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff