A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment
Paper
•
2505.10717
•
Published
•
4
MediPhi
A collection of SLMs based on Phi3.5-mini-instruct adapted to clinical natural language processing tasks: https://arxiv.org/abs/2505.10717
-
-
microsoft/MediPhi-Instruct
Text Generation • 4B • Updated • 2.74k • 55 -
microsoft/MediPhi
Text Generation • 4B • Updated • 1.45k • 12 -
microsoft/MediPhi-PubMed
Text Generation • 4B • Updated • 678 • 8 -
microsoft/MediPhi-Clinical
Text Generation • 4B • Updated • 8.26k • 12 -
microsoft/MediPhi-MedWiki
Text Generation • 4B • Updated • 111 • 2 -
microsoft/MediPhi-Guidelines
Text Generation • 4B • Updated • 91 • 4 -
microsoft/MediPhi-MedCode
Text Generation • 4B • Updated • 112 • 3 -
microsoft/mediflow
Viewer • Updated • 1.84M • 340 • 50 -
microsoft/PatientSafetyBench
Viewer • Updated • 466 • 130 • 2