Instructions to use pucpr/biobertpt-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pucpr/biobertpt-all with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="pucpr/biobertpt-all")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("pucpr/biobertpt-all") model = AutoModelForMaskedLM.from_pretrained("pucpr/biobertpt-all", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Rare Diseases Edge-Case Evaluation Dataset (100k Balanced EHR)
#7
by Synthis-Med-Labs - opened
Hi everyone, we noticed this model lacks fine-tuning data for highly specific sub-vectors like rare EHR syndromes (Susac, Wolfram). We published a 100k balanced synthetic evaluation dataset here: (https://huggingface.co/datasets/Synthis-Med-Labs/rare-diseases-synthetic-clinical-records-100k) to benchmark this exact gap. Let us know if you need customized larger matrices.