Instructions to use dicksonsarpong9/twi-qwen2.5-0.5b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dicksonsarpong9/twi-qwen2.5-0.5b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="dicksonsarpong9/twi-qwen2.5-0.5b-instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dicksonsarpong9/twi-qwen2.5-0.5b-instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dicksonsarpong9/twi-qwen2.5-0.5b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dicksonsarpong9/twi-qwen2.5-0.5b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dicksonsarpong9/twi-qwen2.5-0.5b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dicksonsarpong9/twi-qwen2.5-0.5b-instruct

SGLang

How to use dicksonsarpong9/twi-qwen2.5-0.5b-instruct 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 "dicksonsarpong9/twi-qwen2.5-0.5b-instruct" \
    --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": "dicksonsarpong9/twi-qwen2.5-0.5b-instruct",
		"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 "dicksonsarpong9/twi-qwen2.5-0.5b-instruct" \
        --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": "dicksonsarpong9/twi-qwen2.5-0.5b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dicksonsarpong9/twi-qwen2.5-0.5b-instruct with Docker Model Runner:
```
docker model run hf.co/dicksonsarpong9/twi-qwen2.5-0.5b-instruct
```

🇬🇭 Twi Fine-Tuned Language Model — `twi-qwen2.5-0.5b-instruct`

A Qwen2.5-0.5B-Instruct model fine-tuned on over 1.2 million Twi text examples for instruction-following and text generation in Twi (Akan), a language spoken by over 11 million people in Ghana.

📖 Blog: Building a Twi Language Model — From Data to Deployment

Why Twi?

Twi (also known as Akan Twi or Asante Twi) is one of the most widely spoken languages in Ghana, yet it remains severely underrepresented in modern NLP. Most large language models have little to no understanding of Twi, making them unreliable for Ghanaian users who want to interact in their native language.

This project aims to change that by fine-tuning a capable small language model specifically on Twi data, creating a foundation for Twi-language AI applications.

The Approach

1. Choosing the Base Model

We selected Qwen/Qwen2.5-0.5B-Instruct as our base model for several reasons:

Multilingual foundation: Qwen2.5 was trained on diverse multilingual data, giving it a head start on understanding non-English scripts and character sets
Small but capable: At 0.5B parameters, it's efficient to fine-tune and deploy, even on modest hardware
Instruction-tuned: The instruct variant already understands conversational patterns, so we're adapting an existing capability rather than building from scratch
Open license (Apache 2.0): Freely usable for any purpose

2. Curating the Twi Dataset

We combined two high-quality Twi datasets from the Ghana NLP Community:

Dataset	Size	Description
pristine-twi-english	~999,497 examples	Diverse Twi text spanning narratives, dialogues, monologues, and stories covering Ghanaian culture, politics, sports, and daily life
twi-english-paragraph-dataset_news	~256,797 examples	Twi news paragraphs covering current events, politics, sports, entertainment, and social issues in Ghana

Combined total: ~1,255,641 examples (1,192,858 train / 62,783 eval after a 95/5 split)

Each example was converted into a conversational format compatible with SFT training:

{
  "messages": [
    {"role": "user", "content": "Kyerɛ biribi fa Twi kasa ho."},
    {"role": "assistant", "content": "<twi text from dataset>"}
  ]
}

We filtered out examples shorter than 20 characters to ensure quality.

3. Training Configuration

We used TRL's SFTTrainer (Supervised Fine-Tuning) with the following configuration:

Hyperparameter	Value
Method	Full SFT (Supervised Fine-Tuning)
Epochs	3
Batch size	4 per device
Gradient accumulation	4 steps (effective batch = 16)
Max sequence length	1024 tokens
Learning rate	2e-5
LR scheduler	Cosine
Warmup steps	500
Weight decay	0.01
Precision	bf16
Gradient checkpointing	Enabled
Hardware	NVIDIA A10G (24GB VRAM)
Training time	~6-8 hours

4. Key Implementation Details

Dataset Diversity: By combining narrative, dialogue, monologue, storyful, and news text, the model learns diverse Twi language patterns — from formal news reporting to casual conversation.

Memory Optimization: Gradient checkpointing and bf16 precision allowed us to train the full model (not LoRA) on a single A10G GPU while maintaining a reasonable batch size.

Evaluation: We held out 5% of the data for validation, with eval runs every 200 steps and checkpointing every 400 steps. The best checkpoint (lowest eval loss) is automatically selected.

How to Use the Model

Quick Start

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="dicksonsarpong9/twi-qwen2.5-0.5b-instruct",
    device_map="auto"
)

messages = [{"role": "user", "content": "Kyerɛ me Ghana ho asɛm."}]
response = pipe(messages, max_new_tokens=512, temperature=0.7, do_sample=True)
print(response[0]["generated_text"][-1]["content"])

Detailed Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "dicksonsarpong9/twi-qwen2.5-0.5b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, device_map="auto")

# Format as conversation
messages = [{"role": "user", "content": "Ka biribi fa aduane a Ghanafoɔ di ho."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    temperature=0.7,
    do_sample=True,
    top_p=0.9,
    repetition_penalty=1.1,
)

response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
print(response)

Interactive Chat (CLI)

Save the inference script and run:

# Install dependencies
pip install transformers torch accelerate

# Run examples
python inference_twi.py

# Single prompt
python inference_twi.py --prompt "Ɛdeɛn nti na adesua ho hia?"

# Interactive mode
python inference_twi.py --interactive

Example Prompts to Try

Twi Prompt	English Translation
`Kyerɛ me Ghana ho asɛm.`	Tell me about Ghana.
`Ɛdeɛn ne Twi kasa no mu nsɛm a ɛhia?`	What are important things in the Twi language?
`Ka biribi fa aduane a Ghanafoɔ di ho.`	Say something about Ghanaian food.
`Kyerɛ me ɔkwan a yɛbɛfa so asua Twi kasa.`	Show me how to learn Twi.
`Ɛdeɛn nti na adesua ho hia?`	Why is education important?

Training Data Sources & Acknowledgments

This model was made possible by the incredible work of the Ghana NLP Community, who have been building open-source NLP resources for Ghanaian languages. Their datasets represent a significant effort in documenting and digitizing Twi text across multiple domains.

pristine-twi-english — A large-scale Twi dataset spanning four distinct writing styles (Narrative, Dialogue, Monologue, Storyful)
twi-english-paragraph-dataset_news — Twi-English parallel paragraph dataset from news sources

Limitations

Single-turn focus: The model was trained primarily on single-turn conversations. Multi-turn dialogue quality may be limited.
Twi-only responses: The training focused on Twi text generation. The model may mix English and Twi in some responses, reflecting patterns in the training data.
Knowledge cutoff: The model's knowledge is limited to what was in the base Qwen2.5 model plus the training data.
Small model size: At 0.5B parameters, the model has limited reasoning capacity compared to larger models. It excels at fluent Twi text generation but may struggle with complex reasoning tasks.

Future Work

Add more diverse Twi instruction data (Q&A, summarization, translation)
Train larger variants (Qwen2.5-1.5B, 3B) for improved quality
Add Twi-English translation capabilities
Build evaluation benchmarks for Twi language understanding
Create a Gradio demo Space for easy access

Technical Stack

Component	Tool
Base model	Qwen/Qwen2.5-0.5B-Instruct
Training library	TRL (SFTTrainer)
Experiment tracking	Trackio
Infrastructure	Hugging Face Jobs (A10G GPU)
Dataset library	🤗 Datasets

License

This model is released under the Apache 2.0 license, following the base Qwen2.5 model license.

Citation

If you use this model, please cite:

@misc{twi-qwen2.5-0.5b-instruct,
  author = {Dickson Sarpong},
  title = {Twi Fine-Tuned Qwen2.5-0.5B-Instruct},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/dicksonsarpong9/twi-qwen2.5-0.5b-instruct}
}

Yɛn kasa yɛ kɛseɛ. Our language is great. 🇬🇭

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for dicksonsarpong9/twi-qwen2.5-0.5b-instruct

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(901)

this model

dicksonsarpong9
/

twi-qwen2.5-0.5b-instruct

🇬🇭 Twi Fine-Tuned Language Model — `twi-qwen2.5-0.5b-instruct`

📖 Blog: Building a Twi Language Model — From Data to Deployment

Why Twi?

The Approach

1. Choosing the Base Model

2. Curating the Twi Dataset

3. Training Configuration

4. Key Implementation Details

How to Use the Model

Quick Start

Detailed Usage

Interactive Chat (CLI)

Example Prompts to Try

Training Data Sources & Acknowledgments

Limitations

Future Work

Technical Stack

License

Citation

Model tree for dicksonsarpong9/twi-qwen2.5-0.5b-instruct

Datasets used to train dicksonsarpong9/twi-qwen2.5-0.5b-instruct

🇬🇭 Twi Fine-Tuned Language Model — twi-qwen2.5-0.5b-instruct

📖 Blog: Building a Twi Language Model — From Data to Deployment

Why Twi?

The Approach

1. Choosing the Base Model

2. Curating the Twi Dataset

3. Training Configuration

4. Key Implementation Details

How to Use the Model

Quick Start

Detailed Usage

Interactive Chat (CLI)

Example Prompts to Try

Training Data Sources & Acknowledgments

Limitations

Future Work

Technical Stack

License

Citation

Model tree for dicksonsarpong9/twi-qwen2.5-0.5b-instruct

Datasets used to train dicksonsarpong9/twi-qwen2.5-0.5b-instruct

🇬🇭 Twi Fine-Tuned Language Model — `twi-qwen2.5-0.5b-instruct`