john-osborne-j/quantized-clinicalbert
This repository contains a 4-bit quantized ClinicalBERT model for disease classification based on clinical text. Inspired by CheXNet, this model can predict diseases from patient symptom descriptions, particularly focusing on chest-related conditions.
Implements 4-bit quantization via BitsAndBytes to reduce model footprint while maintaining inference performance, enabling deployment on memory-constrained environments. Trained on synthetic clinical text datasets to avoid privacy constraints, with a Flask web interface for direct symptom-to-disease prediction. Integrates with Hugging Face Transformers and supports Google Colab deployment for accessible prototyping.
No commits in the last 6 months.
Stars
4
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/john-osborne-j/quantized-clinicalbert"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Asha-Gutlapalli/Drug-Recommendation-System-based-on-the-Condition-of-the-Patient-using-BERT
Patients are recommended drugs based on their condition and reviews of the drugs from other...
SPerekrestova/pillchecker-api
Medication interaction checker API (OpenMed + RxNorm + OpenFDA)
Comrade-1729/lex-brief-ai
Safety-first legal NLP system with hierarchical long-document processing, deterministic...
A-SHOJAEI/legal-clause-risk-scorer
A contract clause risk assessment system using DeBERTa-v3-base multi-task learning to identify...
AidanColvin/medical-transcription-specialty-classification
A containerized FastAPI backend that leverages language models to automatically classify medical...