Token Classification
Transformers
Safetensors
English
bert
named-entity-recognition
de-identification
anonymisation
cybersecurity
cyber-incident-reports
Instructions to use GVIS-ULE/rubiner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GVIS-ULE/rubiner with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="GVIS-ULE/rubiner")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("GVIS-ULE/rubiner") model = AutoModelForTokenClassification.from_pretrained("GVIS-ULE/rubiner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add fine-tuned general NER checkpoint
Browse files- config.json +132 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 9,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-AGE",
|
| 14 |
+
"2": "I-AGE",
|
| 15 |
+
"3": "B-AMOUNT_OF_MONEY",
|
| 16 |
+
"4": "I-AMOUNT_OF_MONEY",
|
| 17 |
+
"5": "B-BANK_OR_CARD_NUMBER",
|
| 18 |
+
"6": "I-BANK_OR_CARD_NUMBER",
|
| 19 |
+
"7": "B-CVE",
|
| 20 |
+
"8": "I-CVE",
|
| 21 |
+
"9": "B-DATE",
|
| 22 |
+
"10": "I-DATE",
|
| 23 |
+
"11": "B-EMAIL",
|
| 24 |
+
"12": "I-EMAIL",
|
| 25 |
+
"13": "B-FILE",
|
| 26 |
+
"14": "I-FILE",
|
| 27 |
+
"15": "B-HASH",
|
| 28 |
+
"16": "I-HASH",
|
| 29 |
+
"17": "B-IDENTIFICATION_NUMBER",
|
| 30 |
+
"18": "I-IDENTIFICATION_NUMBER",
|
| 31 |
+
"19": "B-IP",
|
| 32 |
+
"20": "I-IP",
|
| 33 |
+
"21": "B-JOB_TITLE",
|
| 34 |
+
"22": "I-JOB_TITLE",
|
| 35 |
+
"23": "B-LOC",
|
| 36 |
+
"24": "I-LOC",
|
| 37 |
+
"25": "B-MALWARE",
|
| 38 |
+
"26": "I-MALWARE",
|
| 39 |
+
"27": "B-MEDICAL_CONDITION",
|
| 40 |
+
"28": "I-MEDICAL_CONDITION",
|
| 41 |
+
"29": "B-NATIONALITY",
|
| 42 |
+
"30": "I-NATIONALITY",
|
| 43 |
+
"31": "B-OPERATING_SYSTEM",
|
| 44 |
+
"32": "I-OPERATING_SYSTEM",
|
| 45 |
+
"33": "B-ORG",
|
| 46 |
+
"34": "I-ORG",
|
| 47 |
+
"35": "B-PASSWORD",
|
| 48 |
+
"36": "I-PASSWORD",
|
| 49 |
+
"37": "B-PER",
|
| 50 |
+
"38": "I-PER",
|
| 51 |
+
"39": "B-PHONE_NUMBER",
|
| 52 |
+
"40": "I-PHONE_NUMBER",
|
| 53 |
+
"41": "B-QUANTITY",
|
| 54 |
+
"42": "I-QUANTITY",
|
| 55 |
+
"43": "B-SOFTWARE",
|
| 56 |
+
"44": "I-SOFTWARE",
|
| 57 |
+
"45": "B-TIME",
|
| 58 |
+
"46": "I-TIME",
|
| 59 |
+
"47": "B-URL",
|
| 60 |
+
"48": "I-URL",
|
| 61 |
+
"49": "B-USERNAME",
|
| 62 |
+
"50": "I-USERNAME"
|
| 63 |
+
},
|
| 64 |
+
"initializer_range": 0.02,
|
| 65 |
+
"intermediate_size": 3072,
|
| 66 |
+
"label2id": {
|
| 67 |
+
"B-AGE": 1,
|
| 68 |
+
"B-AMOUNT_OF_MONEY": 3,
|
| 69 |
+
"B-BANK_OR_CARD_NUMBER": 5,
|
| 70 |
+
"B-CVE": 7,
|
| 71 |
+
"B-DATE": 9,
|
| 72 |
+
"B-EMAIL": 11,
|
| 73 |
+
"B-FILE": 13,
|
| 74 |
+
"B-HASH": 15,
|
| 75 |
+
"B-IDENTIFICATION_NUMBER": 17,
|
| 76 |
+
"B-IP": 19,
|
| 77 |
+
"B-JOB_TITLE": 21,
|
| 78 |
+
"B-LOC": 23,
|
| 79 |
+
"B-MALWARE": 25,
|
| 80 |
+
"B-MEDICAL_CONDITION": 27,
|
| 81 |
+
"B-NATIONALITY": 29,
|
| 82 |
+
"B-OPERATING_SYSTEM": 31,
|
| 83 |
+
"B-ORG": 33,
|
| 84 |
+
"B-PASSWORD": 35,
|
| 85 |
+
"B-PER": 37,
|
| 86 |
+
"B-PHONE_NUMBER": 39,
|
| 87 |
+
"B-QUANTITY": 41,
|
| 88 |
+
"B-SOFTWARE": 43,
|
| 89 |
+
"B-TIME": 45,
|
| 90 |
+
"B-URL": 47,
|
| 91 |
+
"B-USERNAME": 49,
|
| 92 |
+
"I-AGE": 2,
|
| 93 |
+
"I-AMOUNT_OF_MONEY": 4,
|
| 94 |
+
"I-BANK_OR_CARD_NUMBER": 6,
|
| 95 |
+
"I-CVE": 8,
|
| 96 |
+
"I-DATE": 10,
|
| 97 |
+
"I-EMAIL": 12,
|
| 98 |
+
"I-FILE": 14,
|
| 99 |
+
"I-HASH": 16,
|
| 100 |
+
"I-IDENTIFICATION_NUMBER": 18,
|
| 101 |
+
"I-IP": 20,
|
| 102 |
+
"I-JOB_TITLE": 22,
|
| 103 |
+
"I-LOC": 24,
|
| 104 |
+
"I-MALWARE": 26,
|
| 105 |
+
"I-MEDICAL_CONDITION": 28,
|
| 106 |
+
"I-NATIONALITY": 30,
|
| 107 |
+
"I-OPERATING_SYSTEM": 32,
|
| 108 |
+
"I-ORG": 34,
|
| 109 |
+
"I-PASSWORD": 36,
|
| 110 |
+
"I-PER": 38,
|
| 111 |
+
"I-PHONE_NUMBER": 40,
|
| 112 |
+
"I-QUANTITY": 42,
|
| 113 |
+
"I-SOFTWARE": 44,
|
| 114 |
+
"I-TIME": 46,
|
| 115 |
+
"I-URL": 48,
|
| 116 |
+
"I-USERNAME": 50,
|
| 117 |
+
"O": 0
|
| 118 |
+
},
|
| 119 |
+
"layer_norm_eps": 1e-12,
|
| 120 |
+
"max_position_embeddings": 512,
|
| 121 |
+
"model_type": "bert",
|
| 122 |
+
"num_attention_heads": 12,
|
| 123 |
+
"num_hidden_layers": 12,
|
| 124 |
+
"output_past": true,
|
| 125 |
+
"pad_token_id": 0,
|
| 126 |
+
"position_embedding_type": "absolute",
|
| 127 |
+
"torch_dtype": "float32",
|
| 128 |
+
"transformers_version": "4.53.2",
|
| 129 |
+
"type_vocab_size": 2,
|
| 130 |
+
"use_cache": true,
|
| 131 |
+
"vocab_size": 28996
|
| 132 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46ca08e6e64c001f32780113d409694c20fa9906105818d0966fc5eb20293084
|
| 3 |
+
size 431058932
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_len": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|