Hugging Face's logo

AIdeveric
/
llava-pavement-distress-lora

Image-Text-to-Text
PEFT
Safetensors
English
llava
lora
pavement-distress
structural-health-monitoring
multimodal
vision-language
computer-vision
nlp
conversational
Model card Files
xet
 Community

🛣️ LLaVA-1.5-7B LoRA Adapter - Pavement Distress Analysis

License: MIT Entity F1 Base Model Open In Colab

AI-powered pavement distress analysis using LLaVA-1.5-7B with LoRA fine-tuning.

This repository contains the LoRA adapter achieving 74.31% Entity F1 on pavement distress detection, severity assessment, and maintenance recommendation.

🚀 Quick Start - Try the Demo!

📓 Download and run the Gradio demo notebook:

  1. Download the notebook: LLaVA_Structural_Health_Monitoring_Pavement_Distress_Analyzer.ipynb

  2. Upload to Google Colab:

    • Go to Google Colab
    • Click File → Upload notebook
    • Select the downloaded .ipynb file

  3. Run all cells:

    • Click Runtime → Run all
    • Wait 3-5 minutes for model to load
    • Click the public Gradio link to start analyzing images!

  4. Test with sample images:

    • Download sample images from /images folder
    • Upload to the Gradio interface
    • Get instant distress analysis!

✅ No setup required - runs entirely in the cloud!

Downloads last month
6
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AIdeveric/llava-pavement-distress-lora

Base model

llava-hf/llava-1.5-7b-hf
Adapter
(150)
this model