Token Classification
Transformers
Safetensors
English
roberta
hipaa
phi
protected-health-information
safe-harbor
de-identification
healthcare
medical-records
pii-detection
ner
redaction
privacy
Synthetic
Instructions to use aitrainingdatabroker/hipaa-phi-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aitrainingdatabroker/hipaa-phi-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="aitrainingdatabroker/hipaa-phi-detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("aitrainingdatabroker/hipaa-phi-detector") model = AutoModelForTokenClassification.from_pretrained("aitrainingdatabroker/hipaa-phi-detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from aitrainingdatabroker/hipaa-phi-detector: direct link, hf CLI and curl.
- Browser
- Download file 2.27 kB
-
https://huggingface.co/aitrainingdatabroker/hipaa-phi-detector/resolve/main/config.json
- Command line
-
hf download hf://aitrainingdatabroker/hipaa-phi-detector/config.json
-
curl -L -o config.json https://huggingface.co/aitrainingdatabroker/hipaa-phi-detector/resolve/main/config.json
2.27 kB
| { | |
| "_name_or_path": "distilroberta-base", | |
| "architectures": [ | |
| "RobertaForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-ACCOUNT_NUMBER", | |
| "2": "I-ACCOUNT_NUMBER", | |
| "3": "B-ADDRESS", | |
| "4": "I-ADDRESS", | |
| "5": "B-AGE_OVER_89", | |
| "6": "I-AGE_OVER_89", | |
| "7": "B-DATE", | |
| "8": "I-DATE", | |
| "9": "B-DEVICE_ID", | |
| "10": "I-DEVICE_ID", | |
| "11": "B-EMAIL", | |
| "12": "I-EMAIL", | |
| "13": "B-FAX", | |
| "14": "I-FAX", | |
| "15": "B-HEALTH_PLAN_ID", | |
| "16": "I-HEALTH_PLAN_ID", | |
| "17": "B-IP_ADDRESS", | |
| "18": "I-IP_ADDRESS", | |
| "19": "B-LICENSE_NUMBER", | |
| "20": "I-LICENSE_NUMBER", | |
| "21": "B-MRN", | |
| "22": "I-MRN", | |
| "23": "B-NAME", | |
| "24": "I-NAME", | |
| "25": "B-PHONE", | |
| "26": "I-PHONE", | |
| "27": "B-SSN", | |
| "28": "I-SSN", | |
| "29": "B-URL", | |
| "30": "I-URL", | |
| "31": "B-VEHICLE_ID", | |
| "32": "I-VEHICLE_ID" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-ACCOUNT_NUMBER": 1, | |
| "B-ADDRESS": 3, | |
| "B-AGE_OVER_89": 5, | |
| "B-DATE": 7, | |
| "B-DEVICE_ID": 9, | |
| "B-EMAIL": 11, | |
| "B-FAX": 13, | |
| "B-HEALTH_PLAN_ID": 15, | |
| "B-IP_ADDRESS": 17, | |
| "B-LICENSE_NUMBER": 19, | |
| "B-MRN": 21, | |
| "B-NAME": 23, | |
| "B-PHONE": 25, | |
| "B-SSN": 27, | |
| "B-URL": 29, | |
| "B-VEHICLE_ID": 31, | |
| "I-ACCOUNT_NUMBER": 2, | |
| "I-ADDRESS": 4, | |
| "I-AGE_OVER_89": 6, | |
| "I-DATE": 8, | |
| "I-DEVICE_ID": 10, | |
| "I-EMAIL": 12, | |
| "I-FAX": 14, | |
| "I-HEALTH_PLAN_ID": 16, | |
| "I-IP_ADDRESS": 18, | |
| "I-LICENSE_NUMBER": 20, | |
| "I-MRN": 22, | |
| "I-NAME": 24, | |
| "I-PHONE": 26, | |
| "I-SSN": 28, | |
| "I-URL": 30, | |
| "I-VEHICLE_ID": 32, | |
| "O": 0 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50265 | |
| } | |