Hugging Face's logo

Spaces:
hugging-apps
/
evisrag-multi-image-vqa
Running on Zero

App Files Community
evisrag-multi-image-vqa / README.md
multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
80be33b verified
preview code
|
Raw
History Blame Contribute Delete
1.02 kB

A newer version of the Gradio SDK is available: 6.24.0

Upgrade
metadata 
title: EVisRAG Multi-Image VQA
emoji: 🔍
colorFrom: blue
colorTo: pink
sdk: gradio
sdk_version: 6.21.0
app_file: app.py
short_description: Evidence-guided multi-image visual question answering
python_version: '3.12'
startup_duration_timeout: 30m

EVisRAG-7B: Evidence-Guided Multi-Image VQA

This Space runs EVisRAG-7B (VisRAG 2.0), a multi-image visual question-answering model that mitigates visual hallucinations via evidence-guided reasoning.

Given a question and 1–5 retrieved images, the model:

  1. Observes each image for relevant information
  2. Extracts evidence from each image
  3. Reasons over the collected evidence
  4. Answers the question grounded in the evidence

Based on Qwen2.5-VL-7B-Instruct, fine-tuned with Reward-Scoped GRPO.