Instructions to use mwitiderrick/SwahiliInstruct-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mwitiderrick/SwahiliInstruct-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="mwitiderrick/SwahiliInstruct-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2")
model = AutoModelForCausalLM.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mwitiderrick/SwahiliInstruct-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mwitiderrick/SwahiliInstruct-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mwitiderrick/SwahiliInstruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mwitiderrick/SwahiliInstruct-v0.2

SGLang

How to use mwitiderrick/SwahiliInstruct-v0.2 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 "mwitiderrick/SwahiliInstruct-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mwitiderrick/SwahiliInstruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mwitiderrick/SwahiliInstruct-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mwitiderrick/SwahiliInstruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mwitiderrick/SwahiliInstruct-v0.2 with Docker Model Runner:
```
docker model run hf.co/mwitiderrick/SwahiliInstruct-v0.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SwahiliInstruct-v0.2

This is a Mistral model that has been fine-tuned on the Swahili Alpaca dataset for 3 epochs.

Prompt Template

### Maelekezo:

{query}

### Jibu:
<Leave new line for model to respond>

Usage

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2")
model = AutoModelForCausalLM.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2", device_map="auto")
query = "Nipe maagizo ya kutengeneza mkate wa mandizi"
text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200, do_sample=True, repetition_penalty=1.1)
output = text_gen(f"### Maelekezo:\n{query}\n### Jibu:\n")
print(output[0]['generated_text'])


"""
 Maagizo ya kutengeneza mkate wa mandazi:
1. Preheat tanuri hadi 375°F (190°C).
2. Paka sufuria ya uso na siagi au jotoa sufuria.
3. Katika bakuli la chumvi, ongeza viungo vifuatavyo: unga, sukari ya kahawa, chumvi, mdalasini, na unga wa kakao.
Koroga mchanganyiko pamoja na mbegu za kikombe 1 1/2 za mtindi wenye jamii na hatua ya maji nyepesi.
4. Kando ya uwanja, changanya zaini ya yai 2
"""

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	54.25
AI2 Reasoning Challenge (25-Shot)	55.20
HellaSwag (10-Shot)	78.22
MMLU (5-Shot)	50.30
TruthfulQA (0-shot)	57.08
Winogrande (5-shot)	73.24
GSM8k (5-shot)	11.45

Downloads last month: 10

Safetensors

Model size

7B params

Tensor type

F16

Model tree for mwitiderrick/SwahiliInstruct-v0.2

Base model

mistralai/Mistral-7B-Instruct-v0.2

Finetuned

(1088)

this model

Quantizations

1 model

Dataset used to train mwitiderrick/SwahiliInstruct-v0.2

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

55.200
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

78.220
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

50.300
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

57.080
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

73.240
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

11.450