Instructions to use Lugha-Llama/Lugha-Llama-8B-wura_math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lugha-Llama/Lugha-Llama-8B-wura_math with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Lugha-Llama/Lugha-Llama-8B-wura_math")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lugha-Llama/Lugha-Llama-8B-wura_math")
model = AutoModelForCausalLM.from_pretrained("Lugha-Llama/Lugha-Llama-8B-wura_math")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lugha-Llama/Lugha-Llama-8B-wura_math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lugha-Llama/Lugha-Llama-8B-wura_math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lugha-Llama/Lugha-Llama-8B-wura_math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lugha-Llama/Lugha-Llama-8B-wura_math

SGLang

How to use Lugha-Llama/Lugha-Llama-8B-wura_math with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Lugha-Llama/Lugha-Llama-8B-wura_math" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lugha-Llama/Lugha-Llama-8B-wura_math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Lugha-Llama/Lugha-Llama-8B-wura_math" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lugha-Llama/Lugha-Llama-8B-wura_math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lugha-Llama/Lugha-Llama-8B-wura_math with Docker Model Runner:
```
docker model run hf.co/Lugha-Llama/Lugha-Llama-8B-wura_math
```

Lugha-Llama: Adapting Large Language Models for African Languages

Authors: Happy Buzaaba, Alexander Wettig, David Ifeoluwa Adelani, Christiane Fellbaum

Low-resource african languages remain underrepresented in the large training datasets of large language models (LLMs) and, as a result, LLMs struggle to understand these languages. We are releasing three African-centric Lugha-Llama models based on Llama-3.1-8B, which achieve the best performance among open-source models on IrokoBench, a challenging African languages benchmark and AfriQA, a cross-lingual open-retrieval question answering dataset for African languages (Lugha is the Kiswahili word for "language").

All Lugha-Llama models are available on 🤗 huggingface hub.

Read about the findings in this Lugha-Llama blog post.

For the details and findings check the Lugha-Llama paper

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

F32

Papers for Lugha-Llama/Lugha-Llama-8B-wura_math

Lugha-Llama: Adapting Large Language Models for African Languages

Paper • 2504.06536 • Published Apr 9, 2025

IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models

Paper • 2406.03368 • Published Jun 5, 2024

AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages

Paper • 2305.06897 • Published May 11, 2023 • 9