Token Classification
Transformers
ONNX
Safetensors
English
Irish
distilbert
pii
de-identification
ireland
irish
gaelic
raw-only
ppsn
eircode
passport
phone-number
int8
dynamic-quantization
Instructions to use temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8") model = AutoModel.from_pretrained("temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "models/openmed-mliteclinical-irish-core-span-rc8f_gapunct_cal", | |
| "init_span_model": "models/openmed-mliteclinical-irish-core-span-rc8f_gapunct_cal", | |
| "init_token_model": "release/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc7", | |
| "label_names": [ | |
| "ACCOUNT_NUMBER", | |
| "BANK_ROUTING_NUMBER", | |
| "CREDIT_DEBIT_CARD", | |
| "EMAIL", | |
| "FIRST_NAME", | |
| "LAST_NAME", | |
| "PASSPORT_NUMBER", | |
| "PHONE_NUMBER", | |
| "POSTCODE", | |
| "PPSN", | |
| "SWIFT_BIC" | |
| ], | |
| "max_length": 128, | |
| "task": "Irish core PII token-presence plus start/end span extraction", | |
| "freeze_layers": 2, | |
| "span_positive_weight": 6.0, | |
| "token_positive_weight": 4.0, | |
| "token_presence_weight": 1.0, | |
| "boundary_loss_weight": 1.0, | |
| "boundary_smoothing": 0.15, | |
| "fitted_label_max_span_tokens": { | |
| "ACCOUNT_NUMBER": 19, | |
| "BANK_ROUTING_NUMBER": 6, | |
| "CREDIT_DEBIT_CARD": 13, | |
| "EMAIL": 16, | |
| "FIRST_NAME": 5, | |
| "LAST_NAME": 8, | |
| "PASSPORT_NUMBER": 9, | |
| "PHONE_NUMBER": 10, | |
| "POSTCODE": 8, | |
| "PPSN": 9, | |
| "SWIFT_BIC": 8 | |
| }, | |
| "train_examples": 30000, | |
| "valid_examples": 3750, | |
| "test_examples": 3750, | |
| "data": "data/irish_core_multitask_rc8_mix_v1" | |
| } | |