Instructions to use SOTAagi2030/ClinicNote-DeID-Baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SOTAagi2030/ClinicNote-DeID-Baseline with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="SOTAagi2030/ClinicNote-DeID-Baseline")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("SOTAagi2030/ClinicNote-DeID-Baseline") model = AutoModelForTokenClassification.from_pretrained("SOTAagi2030/ClinicNote-DeID-Baseline", device_map="auto") - Notebooks
- Google Colab
- Kaggle
ClinicNote DeID Baseline
This release packages a token-classification baseline for removing direct identifiers from synthetic outpatient notes.
Intended use
Use this checkpoint only for research and pipeline prototyping with synthetic or appropriately governed text. Review all outputs before any downstream use.
Validation snapshot
The selected candidate was evaluated on the held-out synthetic clinic-note validation split. The selection criterion was validation F1.
Files
model.safetensors: model weightsconfig.json: model configurationtokenizer.json: tokenizer definitionassets/redaction-example.txt: a redaction example
- Downloads last month
- -