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 • 1.72k • 56 -
microsoft/MediPhi
Text Generation • 4B • Updated • 357 • 14 -
microsoft/MediPhi-PubMed
Text Generation • 4B • Updated • 419 • 8 -
microsoft/MediPhi-Clinical
Text Generation • 4B • Updated • 2.58k • 12 -
microsoft/MediPhi-MedWiki
Text Generation • 4B • Updated • 98 • 2 -
microsoft/MediPhi-Guidelines
Text Generation • 4B • Updated • 93 • 4 -
microsoft/MediPhi-MedCode
Text Generation • 4B • Updated • 216 • 5 -
microsoft/mediflow
Viewer • Updated • 1.84M • 276 • 51 -
microsoft/PatientSafetyBench
Viewer • Updated • 466 • 137 • 2