Downloads · 30 days
3
3% of all-time downloads
rayserve/qwen35-27b-afri-health-qa-lora
qwen35-27b-afri-health-qa-lora is a text generation model from rayserve. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
A single LoRA adapter for answering maternal, sexual and reproductive-health questions written in English and several African languages (Swahili, Luganda, Amharic, Akan).
Downloads · 30 days
3
3% of all-time downloads
All-time downloads
87
Public
Repo size
1.9 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.9 GB · 99%
From the Hugging Face model README
A single LoRA adapter for answering maternal, sexual and reproductive-health questions written in English and several African languages (Swahili, Luganda, Amharic, Akan).
This repository contains the LoRA adapter only. To run inference you must download the base model
Qwen/Qwen3.5-27Bseparately and attach this adapter to it — the adapter on its own cannot generate.
Every question is answered in context: a few nearest same-language question/answer precedents are retrieved from a reference pool and placed in front of the question, and the model is asked to answer by leaning on them. Training and inference use the exact same layout, so one adapter is enough.
Generating grounded answers to health questions in the supported languages, for research and benchmark evaluation. Given a question and its retrieved precedents, the model returns a single answer in the question's language.
vllm, sentence-transformers, pandas, numpy,
huggingface_hubMcGill-NLP/AfriE5-Large-instruct) to build the
precedent blockQwen/Qwen3.5-27BOpen inference.ipynb and run it top to bottom. It will:
submission.csv.Set the environment variable LIMIT=16 first for a quick smoke test, or leave it
unset to score the whole test set. Point BASE_MODEL / ADAPTER_REPO at local
folders if you already have them.
inference.ipynb regenerates submission.csv and runs structural checks
(columns, target consistency, id ordering, no empty rows). The reported score is
verified by uploading that file to the benchmark.
A note on variance. vLLM strongly affects both fine-tuning and inference — re-running the same recipe through vLLM can move the score by up to ±0.004 on both public and private. This has been observed repeatedly across many runs, so the reported number should be read as a point within that band, not an exact target.