You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen2.5-VL MEDVQA-GI 2026 Subtask 1

Team: CSmorgan

This repository contains the official Task 1 submission files for MEDVQA-GI Subtask 1.

Base model:

Qwen/Qwen2.5-VL-7B-Instruct

Adapter checkpoint:

checkpoint-500/

This model was fine-tuned with LoRA/QLoRA for gastrointestinal endoscopy visual question answering.

Research use only. Not intended for clinical deployment.

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Adapter

(355)

this model