Text Generation
PEFT
Safetensors
lora
medical
health
multilingual
africa
question-answering
zindi
mhqa-itu
Instructions to use DariusTheGeek/mhqa-itu-adapters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use DariusTheGeek/mhqa-itu-adapters with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
fix GitHub URL -> Multilingual-Health-QA-ITU-Zindi-Challenge
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ hosted on Zindi. Data by the **HASH** consortium (Hub for AI in Maternal, Sexual
|
|
| 31 |
|
| 32 |
This repo hosts **3 LoRA adapters** (the generation members). The full retrieval + generation + judge
|
| 33 |
**system**, and one-command reproduction, live in the code repo:
|
| 34 |
-
**[
|
| 35 |
|
| 36 |
> ⚠️ **Not medical advice.** This is a research artifact built for a benchmark competition. It is **not a
|
| 37 |
> medical device**, is **not for clinical use**, and its outputs must not be used to diagnose, treat, or make
|
|
@@ -127,8 +127,8 @@ is byte-identical to the scored `sub_v40`.
|
|
| 127 |
The adapters are components of a pipeline — use the GitHub repo, which pulls these weights automatically:
|
| 128 |
|
| 129 |
```bash
|
| 130 |
-
git clone https://github.com/DariusTheGeek/Multilingual-Health-
|
| 131 |
-
cd Multilingual-Health-
|
| 132 |
bash env/install.sh
|
| 133 |
bash stages/0_setup/fetch_artifacts.sh # ~250 MB data/features (Path A, CPU)
|
| 134 |
bash reproduce.sh # -> sub_v40, BYTE-IDENTICAL, minutes, no GPU
|
|
|
|
| 31 |
|
| 32 |
This repo hosts **3 LoRA adapters** (the generation members). The full retrieval + generation + judge
|
| 33 |
**system**, and one-command reproduction, live in the code repo:
|
| 34 |
+
**[Multilingual-Health-QA-ITU-Zindi-Challenge on GitHub](https://github.com/DariusTheGeek/Multilingual-Health-QA-ITU-Zindi-Challenge)**.
|
| 35 |
|
| 36 |
> ⚠️ **Not medical advice.** This is a research artifact built for a benchmark competition. It is **not a
|
| 37 |
> medical device**, is **not for clinical use**, and its outputs must not be used to diagnose, treat, or make
|
|
|
|
| 127 |
The adapters are components of a pipeline — use the GitHub repo, which pulls these weights automatically:
|
| 128 |
|
| 129 |
```bash
|
| 130 |
+
git clone https://github.com/DariusTheGeek/Multilingual-Health-QA-ITU-Zindi-Challenge.git
|
| 131 |
+
cd Multilingual-Health-QA-ITU-Zindi-Challenge
|
| 132 |
bash env/install.sh
|
| 133 |
bash stages/0_setup/fetch_artifacts.sh # ~250 MB data/features (Path A, CPU)
|
| 134 |
bash reproduce.sh # -> sub_v40, BYTE-IDENTICAL, minutes, no GPU
|