MedSwin
/

MedSwin-KD-SFT-PubMed-l

Question Answering

Model card Files Files and versions

Developed by: Medical Swinburne University of Technology AI Team
Funded by: Swinburne University of Technology
Language(s): English
License: Apache 2.0

Model Details

This is a Supervised Finetuning (SFT) model on top of a Knowledge Distillation model (KD), on labelled dataset from PubMedQA.

Review all model metrics benchmark via Benchmark Document Preview.

Downloads last month: 7

Safetensors

Model size

7B params

Tensor type

F16

·

Model tree for MedSwin/MedSwin-KD-SFT-PubMed-l

Base model

google/gemma-3-27b-pt

Finetuned

google/medgemma-27b-it

Finetuned

MedSwin/MedSwin-7B-KD

Finetuned

(2)

this model

Quantizations

Dataset used to train MedSwin/MedSwin-KD-SFT-PubMed-l

Collection including MedSwin/MedSwin-KD-SFT-PubMed-l

Model

Model mix • 12 items • Updated Mar 2 • 3