MedM-VL-2D-3B-en

shiym2000/MedM-VL-2D-3B-en

MedM-VL-2D-3B-en is a image-text-to-text model from shiym2000. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

A 2D medical LVLM trained on 2D medical images and English medical texts, enabling tasks such as report generation, VQA, referring expression comprehension (REC), referring expression generation (REG) and image classi…

Downloads · 30 days

122

14% of all-time downloads

All-time downloads

850

Public

Parameters

3.5B

13.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors7 GB · 100%

At a glance

Task: Image-Text-to-Text
License: apache-2.0
Model type: lvlm
Access: Public
Created: Apr 10, 2025
Updated: Oct 11, 2025
SHA: a6cd6d36

Try a prompt

Base models

Model card

From the Hugging Face model README

MedM-VL-2D-3B-en

Introduction

A 2D medical LVLM trained on 2D medical images and English medical texts, enabling tasks such as report generation, VQA, referring expression comprehension (REC), referring expression generation (REG) and image classification.

	Config
Image encoder	google/siglip-base-patch16-256-multilingual
Connector	MLP (2-layer)
LLM	Qwen/Qwen2.5-3B-Instruct
Image resolution	256*256
Sequence length	2048

Evaluation

Benchmark	Med-Flamingo	LLaVA-Med	RadFM	MedM-VL-2D-3B-en
MedMNIST<sub>derma</sub>	0.012	0.258	0.051	0.810
MedMNIST<sub>organ</sub>	0.089	0.668	0.189	0.791
MedPix	0.081	0.151	-	0.087
MIMIC-CXR	0.233	0.204	0.068	0.222
PathVQA	0.334	0.378	0.248	0.634
SAMed<sub>identify</sub>	-	0.458	-	0.637
SAMed<sub>refer</sub>	-	0.086	-	0.225
SLAKE<sub>identify</sub>	-	0.272	-	0.349
SLAKE<sub>refer</sub>	-	0.041	-	0.261
SLAKE<sub>vqa</sub>	0.215	0.337	0.817	0.812

Quickstart

Please refer to MedM-VL.

Citation

@inproceedings{shi2025medm,
  title={Medm-vl: What makes a good medical lvlm?},
  author={Shi, Yiming and Yang, Shaoshuai and Zhu, Xun and Wang, Haoyu and Fu, Xiangling and Li, Miao and Wu, Ji},
  booktitle={International Workshop on Agentic AI for Medicine},
  pages={290--299},
  year={2025},
  organization={Springer}
}

Task: Image-Text-to-Text
Type: lvlm
License: apache-2.0
Languages: en
Created: Apr 10, 2025
Updated: Oct 11, 2025