Edifon/SOAP_SFT_V1
VISIONConcurrency Cost:1Model Size:4.3BQuant:BF16Ctx Length:32kPublished:Mar 14, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Edifon's SOAP_SFT_V1 is a 4.3 billion parameter causal language model, fine-tuned from Gemma 3 4B Instruct, specifically designed to generate structured medical SOAP notes (Subjective, Objective, Assessment, Plan) from doctor-patient dialogues. Optimized for clinical NLP research and healthcare professionals, it excels at converting consultation transcripts into the standardized SOAP format. The model was trained using Supervised Fine-Tuning with LoRA on a dataset of 9,250 medical dialogues, achieving stable convergence over 5 epochs.

Loading preview...