medgemma-decide-4b-v2

medgemma-decide-4b-v2 scores medical text options for research only. Read its class-balance gains, regressions and HAI-DEF licence terms.

By Amaljith · Weights upload: 7 Nov 2026

An English medical-text decision fine-tune continued from a MedGemma 1.5 4B derivative. It scores typed options without generated text. Minority-class oversampling changes the decision balance, with gains and regressions across questions. Research use only, not for diagnosis, triage, clinical decisions or patient care.

Quick answers

Facts

Base

unsloth/medgemma-1.5-4b-it, continued from the maker’s first released checkpoint

Inputs

English medical text and supplied typed options; text only

Training

Fresh rank-16 LoRA; one epoch, 728 steps, 51.7 minutes on an A100 80 GB, according to the card

Licence

Health AI Developer Foundations terms; derivative notice included

Access

Public merged weights, joint decision head, adapter, inference code and per-question temperatures

Claims and sources

• The maker reports medline/adverse balanced accuracy rising from 0.625 to 0.825, above its TF-IDF baseline floor of 0.721. Macro balanced accuracy across sources falls from 0.689 to 0.686. The evaluation has 15,320 records and 19,480 decisions; balanced accuracy uses a prior-adjusted decision rule. vendor reportedsource
• The card reports PubMedQA balanced accuracy falling from 0.578 to 0.488 under that rule. Public exam sets, MeSH labels and one seed per run limit interpretation; seed variance is unmeasured. This is not clinical validation. vendor reportedsource

Links

Source: Model card and weights → Source: Per-question results → Source: Derivative notice →

Related projects

No related projects are listed in the registry.

All projects · Back to the model registry