Spaces:
Sleeping
Sleeping
Upload 7 files
Browse files- indiaai-text-classification-model/config.json +63 -0
- indiaai-text-classification-model/model.safetensors +3 -0
- indiaai-text-classification-model/special_tokens_map.json +7 -0
- indiaai-text-classification-model/tokenizer.json +0 -0
- indiaai-text-classification-model/tokenizer_config.json +55 -0
- indiaai-text-classification-model/training_args.bin +3 -0
- indiaai-text-classification-model/vocab.txt +0 -0
indiaai-text-classification-model/config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 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": "RapeGang Rape RGRSexually Abusive Content",
|
| 14 |
+
"1": "Hacking Damage to computercomputer system etc",
|
| 15 |
+
"2": "Report Unlawful Content",
|
| 16 |
+
"3": "Online Financial Fraud",
|
| 17 |
+
"4": "Cyber Terrorism",
|
| 18 |
+
"5": "Online Gambling Betting",
|
| 19 |
+
"6": "Crime Against Women & Children",
|
| 20 |
+
"7": "Ransomware",
|
| 21 |
+
"8": "Online Cyber Trafficking",
|
| 22 |
+
"9": "Sexually Explicit Act",
|
| 23 |
+
"10": "Child Pornography CPChild Sexual Abuse Material CSAM",
|
| 24 |
+
"11": "Sexually Obscene material",
|
| 25 |
+
"12": "Any Other Cyber Crime",
|
| 26 |
+
"13": "Cyber Attack/ Dependent Crimes",
|
| 27 |
+
"14": "Cryptocurrency Crime",
|
| 28 |
+
"15": "Online and Social Media Related Crime"
|
| 29 |
+
},
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"Any Other Cyber Crime": 12,
|
| 34 |
+
"Child Pornography CPChild Sexual Abuse Material CSAM": 10,
|
| 35 |
+
"Crime Against Women & Children": 6,
|
| 36 |
+
"Cryptocurrency Crime": 14,
|
| 37 |
+
"Cyber Attack/ Dependent Crimes": 13,
|
| 38 |
+
"Cyber Terrorism": 4,
|
| 39 |
+
"Hacking Damage to computercomputer system etc": 1,
|
| 40 |
+
"Online Cyber Trafficking": 8,
|
| 41 |
+
"Online Financial Fraud": 3,
|
| 42 |
+
"Online Gambling Betting": 5,
|
| 43 |
+
"Online and Social Media Related Crime": 15,
|
| 44 |
+
"Ransomware": 7,
|
| 45 |
+
"RapeGang Rape RGRSexually Abusive Content": 0,
|
| 46 |
+
"Report Unlawful Content": 2,
|
| 47 |
+
"Sexually Explicit Act": 9,
|
| 48 |
+
"Sexually Obscene material": 11
|
| 49 |
+
},
|
| 50 |
+
"layer_norm_eps": 1e-12,
|
| 51 |
+
"max_position_embeddings": 512,
|
| 52 |
+
"model_type": "bert",
|
| 53 |
+
"num_attention_heads": 12,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"pad_token_id": 0,
|
| 56 |
+
"position_embedding_type": "absolute",
|
| 57 |
+
"problem_type": "single_label_classification",
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.46.0",
|
| 60 |
+
"type_vocab_size": 2,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 30522
|
| 63 |
+
}
|
indiaai-text-classification-model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52ea8e7a568e35af16e88d3b5d792f23148036057cd9383c75618f5f73e8394f
|
| 3 |
+
size 438001712
|
indiaai-text-classification-model/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 |
+
}
|
indiaai-text-classification-model/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
indiaai-text-classification-model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
indiaai-text-classification-model/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c1fbbfb54fc0271865dad4e29681140bcfbfe0e3159706c1653c409db89f44c
|
| 3 |
+
size 5176
|
indiaai-text-classification-model/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|