Instructions to use UMCU/PII_RobBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UMCU/PII_RobBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="UMCU/PII_RobBERT", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("UMCU/PII_RobBERT", trust_remote_code=True) model = AutoModelForTokenClassification.from_pretrained("UMCU/PII_RobBERT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "additional_special_tokens_ids": [], | |
| "architectures": [ | |
| "TokenClassificationModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "auto_map": { | |
| "AutoModelForTokenClassification": "modeling.TokenClassificationModel" | |
| }, | |
| "backbone_model_name": "DTAI-KULeuven/robbert-2023-dutch-large", | |
| "bos_token_id": 0, | |
| "class_weights": [ | |
| 1.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 10.665912628173828, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 29.357572555541992, | |
| 50.0, | |
| 50.0, | |
| 30.548648834228516, | |
| 11.926840782165527, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 33.347381591796875, | |
| 10.019938468933105, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 50.0, | |
| 47.132938385009766, | |
| 50.0, | |
| 50.0, | |
| 50.0 | |
| ], | |
| "classifier_dropout": 0.1, | |
| "classifier_hidden_layers": [ | |
| 768, | |
| 768, | |
| 768 | |
| ], | |
| "cls_token_id": 0, | |
| "custom_model_type": "TokenClassificationModel", | |
| "dtype": "bfloat16", | |
| "eos_token_id": 3, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-AGE", | |
| "2": "I-AGE", | |
| "3": "B-BUILDINGNUM", | |
| "4": "I-BUILDINGNUM", | |
| "5": "B-CITY", | |
| "6": "I-CITY", | |
| "7": "B-CREDITCARDNUMBER", | |
| "8": "I-CREDITCARDNUMBER", | |
| "9": "B-DATE", | |
| "10": "I-DATE", | |
| "11": "B-DRIVERLICENSENUM", | |
| "12": "I-DRIVERLICENSENUM", | |
| "13": "B-EMAIL", | |
| "14": "I-EMAIL", | |
| "15": "B-GENDER", | |
| "16": "I-GENDER", | |
| "17": "B-GIVENNAME", | |
| "18": "I-GIVENNAME", | |
| "19": "B-IDCARDNUM", | |
| "20": "I-IDCARDNUM", | |
| "21": "B-PASSPORTNUM", | |
| "22": "I-PASSPORTNUM", | |
| "23": "B-SEX", | |
| "24": "I-SEX", | |
| "25": "B-SOCIALNUM", | |
| "26": "I-SOCIALNUM", | |
| "27": "B-STREET", | |
| "28": "I-STREET", | |
| "29": "B-SURNAME", | |
| "30": "I-SURNAME", | |
| "31": "B-TAXNUM", | |
| "32": "I-TAXNUM", | |
| "33": "B-TELEPHONENUM", | |
| "34": "I-TELEPHONENUM", | |
| "35": "B-TITLE", | |
| "36": "I-TITLE", | |
| "37": "B-ZIPCODE", | |
| "38": "I-ZIPCODE" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "label2id": { | |
| "B-AGE": 1, | |
| "B-BUILDINGNUM": 3, | |
| "B-CITY": 5, | |
| "B-CREDITCARDNUMBER": 7, | |
| "B-DATE": 9, | |
| "B-DRIVERLICENSENUM": 11, | |
| "B-EMAIL": 13, | |
| "B-GENDER": 15, | |
| "B-GIVENNAME": 17, | |
| "B-IDCARDNUM": 19, | |
| "B-PASSPORTNUM": 21, | |
| "B-SEX": 23, | |
| "B-SOCIALNUM": 25, | |
| "B-STREET": 27, | |
| "B-SURNAME": 29, | |
| "B-TAXNUM": 31, | |
| "B-TELEPHONENUM": 33, | |
| "B-TITLE": 35, | |
| "B-ZIPCODE": 37, | |
| "I-AGE": 2, | |
| "I-BUILDINGNUM": 4, | |
| "I-CITY": 6, | |
| "I-CREDITCARDNUMBER": 8, | |
| "I-DATE": 10, | |
| "I-DRIVERLICENSENUM": 12, | |
| "I-EMAIL": 14, | |
| "I-GENDER": 16, | |
| "I-GIVENNAME": 18, | |
| "I-IDCARDNUM": 20, | |
| "I-PASSPORTNUM": 22, | |
| "I-SEX": 24, | |
| "I-SOCIALNUM": 26, | |
| "I-STREET": 28, | |
| "I-SURNAME": 30, | |
| "I-TAXNUM": 32, | |
| "I-TELEPHONENUM": 34, | |
| "I-TITLE": 36, | |
| "I-ZIPCODE": 38, | |
| "O": 0 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "mask_token_id": 4, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "requires_trust_remote_code": true, | |
| "sep_token_id": 3, | |
| "tokenizer_class": "RobertaTokenizerFast", | |
| "transformers_version": "4.57.6", | |
| "type_vocab_size": 1, | |
| "unk_token_id": 2, | |
| "use_cache": true, | |
| "vocab_size": 50000 | |
| } | |