socsys commited on
Commit
580ee10
·
verified ·
1 Parent(s): a196f5f

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,4 @@
1
- ---
2
- license: mit
3
- ---
 
 
1
+ # toxic-bert
2
+
3
+ Stage the remote toxicity classifier assets here before uploading to Hugging Face.
4
+ Expected runtime repo id: `Xenova/toxic-bert` or your pinned mirror.
SHA256SUMS ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ e2c6937717530ce48ea753182c5558c8b285a0e1dd7824759d63a81adce28447 ./config.json
2
+ c4dfb3f96991081b820694578d2b07374dbe61c2032bba4ace4fa0f18022a6b7 ./deployment_metadata.json
3
+ 70b5abe097a45c1e267a2eabfd58df03df4d790518b6b13d700137bbf34d7a31 ./extension_compat.json
4
+ 620012c9bed13e3c58b9c959d160d955ff033a1a27528212b9da5b0aa4ac3f73 ./onnx/model_quantized.onnx
5
+ 64bfa9a6cddba342766ae20724d80ac05c408b79dbca99f957296c46f47d10eb ./README.md
6
+ b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3 ./special_tokens_map.json
7
+ 9261e7d79b44c8195c1cada2b453e55b00aeb81e907a6664974b4d7776172ab3 ./tokenizer_config.json
8
+ d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66 ./tokenizer.json
9
+ 07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3 ./vocab.txt
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unitary/toxic-bert",
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": "toxic",
14
+ "1": "severe_toxic",
15
+ "2": "obscene",
16
+ "3": "threat",
17
+ "4": "insult",
18
+ "5": "identity_hate"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "identity_hate": 5,
24
+ "insult": 4,
25
+ "obscene": 2,
26
+ "severe_toxic": 1,
27
+ "threat": 3,
28
+ "toxic": 0
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 0,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "multi_label_classification",
38
+ "transformers_version": "4.32.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 30522
42
+ }
deployment_metadata.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modelId": "Xenova/toxic-bert",
3
+ "sourceModel": "Xenova/toxic-bert",
4
+ "runtime": "transformers.js-onnxruntime-web-wasm-cpu",
5
+ "task": "text-classification",
6
+ "quantized": true,
7
+ "classifierLabels": [
8
+ "toxic",
9
+ "severe_toxic",
10
+ "obscene",
11
+ "threat",
12
+ "insult",
13
+ "identity_hate"
14
+ ],
15
+ "artifacts": {
16
+ "config": "config.json",
17
+ "tokenizer": "tokenizer.json",
18
+ "tokenizerConfig": "tokenizer_config.json",
19
+ "specialTokens": "special_tokens_map.json",
20
+ "vocab": "vocab.txt",
21
+ "onnx": "onnx/model_quantized.onnx"
22
+ },
23
+ "releaseState": "staged-for-upload"
24
+ }
extension_compat.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modelId": "Xenova/toxic-bert",
3
+ "format": "transformers.js",
4
+ "runtime": {
5
+ "transformers": "2.17.2",
6
+ "onnxruntimeWeb": "1.14.x"
7
+ },
8
+ "extension": {
9
+ "minimumVersion": "5.0.0",
10
+ "supportedModes": ["detoxicify"]
11
+ },
12
+ "files": [
13
+ "config.json",
14
+ "deployment_metadata.json",
15
+ "extension_compat.json",
16
+ "onnx/model_quantized.onnx",
17
+ "special_tokens_map.json",
18
+ "tokenizer.json",
19
+ "tokenizer_config.json",
20
+ "vocab.txt"
21
+ ]
22
+ }
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620012c9bed13e3c58b9c959d160d955ff033a1a27528212b9da5b0aa4ac3f73
3
+ size 110720344
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff