---
license: apache-2.0
language:
- en
- ha
- yo
- fr
tags:
- healthcare
- nigeria
- wash
- environmental-health
- africa
- autoscientist
base_model: meta-llama/Llama-3.3-70B-Instruct
---

# Nigeria WASH Health Model
### AutoScientist Challenge 2026 | Healthcare Category

**Author:** Hussein Adeiza (mabera)  
**Role:** Licensed Environmental Health Officer, Abuja Nigeria  
**Base Model:** Llama 3.3 70B  
**Fine-tuned with:** AutoScientist by Adaption Labs  

## Model Description
This is a LoRA adapter fine-tuned on Nigeria DHS WASH health data (2003–2024). 
It predicts and explains child diarrhea risk from water, sanitation and hygiene indicators across Nigeria.

## Training Data
- Source: DHS Nigeria national surveys (2003–2024)
- Dataset: 3,972 adapted rows (Hausa, Yoruba, French, English)
- Quality improvement: 310% (Grade E → B)
- Kaggle: https://www.kaggle.com/datasets/yunusahusseinadeiza/nigeria-wash-risk-model-diarrhea-prediction

## Training Metrics
- Win rate: ~70% adapted vs ~30% base model
- Base model: meta-llama/Llama-3.3-70B-Instruct
- Method: LoRA (r=16, alpha=32, all-linear)
- Epochs: 1

## Why This Matters
Most health AI is trained on Western clinical data. 
This model addresses the gap in African environmental health AI — 
built specifically for Nigerian and West African public health realities.

## Credits
Powered by Adaptive Data — Adaption Labs  
AutoScientist Challenge 2026