DariusTheGeek commited on
Commit
16247b4
·
verified ·
1 Parent(s): 6c93441

fix GitHub URL -> Multilingual-Health-QA-ITU-Zindi-Challenge

Browse files
Files changed (1) hide show
  1. README.md +3 -3
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
- **[…-ITU-SOLUTION on GitHub](https://github.com/DariusTheGeek/Multilingual-Health-Question-Answering-in-Low-Resource-African-Languages-Challenge-by-ITU-SOLUTION)**.
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-Question-Answering-in-Low-Resource-African-Languages-Challenge-by-ITU-SOLUTION.git
131
- cd Multilingual-Health-…-SOLUTION
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