It is designed to explore small, accessible language models for Nigerian-context communication, including customer service, Nigerian English, basic Nigerian Pidgin, professional boundaries, business writing, and scam-safety guidance.

Important status

This is an early research release.

The adapter was trained on a small, manually reviewed dataset of 47 examples. It should not be treated as a production-ready general-purpose assistant.

The current release demonstrates a reproducible workflow for:

creating training examples from CSV
generating JSONL training data
validating dataset structure
detecting duplicate IDs and prompts
calculating dataset statistics
training a CPU-compatible LoRA adapter
versioning model releases

Model details

Field	Value
Model	GaiaLab Naija Assistant v0.5
Base model	`Qwen/Qwen2.5-0.5B-Instruct`
Fine-tuning method	LoRA / PEFT
Model type	Causal language model adapter
Primary language	English
Additional language variety	Nigerian English and basic Nigerian Pidgin
Training examples	47
Dataset health score	95/100
Developer	Oluwafemi Idiakhoa
Project	GaiaLab AI

Training-data categories

The v0.5 training dataset contained:

Category	Examples
Safety and scams	13
Professional boundaries	12
Customer service	10
Nigerian English	10
Business writing	1
Nigerian Pidgin	1
Total	47

Risk-level distribution:

Risk level	Examples
High	19
Medium	7
Low	21

Dataset validation

The dataset pipeline reported:

valid JSONL structure
required fields present
correct system, user, and assistant message order
zero duplicate IDs
zero duplicate prompts
zero missing prompts
zero missing responses
dataset health score of 95/100

Intended uses

This adapter may be useful for:

research on Nigerian-context conversational AI
educational demonstrations of LoRA fine-tuning
Nigerian customer-service prototypes
professional-message drafting experiments
scam-awareness and credential-safety demonstrations
Nigerian English and basic Pidgin experimentation
CPU-friendly small-model research

Out-of-scope uses

This model should not be used as the sole authority for:

medical decisions
legal advice
financial decisions
banking authentication
emergency response
employment decisions
identity verification
high-impact automated decision-making

Never provide passwords, PINs, one-time passwords, bank verification codes, private keys, or other sensitive credentials to the model.

Installation

pip install torch transformers peft

Usage

python

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model_id = "Qwen/Qwen2.5-0.5B-Instruct"
adapter_id = "mgbam/gaialab-naija-adapter-v0.5"

tokenizer = AutoTokenizer.from_pretrained(
    base_model_id,
    trust_remote_code=True,
)

base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float32,
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(
    base_model,
    adapter_id,
)

messages = [
    {
        "role": "system",
        "content": (
            "You are GaiaLab Naija Assistant. Be helpful, concise, "
            "culturally aware, truthful, and safe."
        ),
    },
    {
        "role": "user",
        "content": "Write a polite reminder for a customer who has not paid.",
    },
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    output = model.generate(
        **inputs,
        max_new_tokens=120,
        do_sample=False,
    )

generated_tokens = output[0][inputs["input_ids"].shape[1]:]
response = tokenizer.decode(
    generated_tokens,
    skip_special_tokens=True,
)

print(response)

Example areas

The adapter was trained on examples involving:

suspicious requests for OTPs and PINs
safe handling of account credentials
professional customer responses
Nigerian-style business communication
polite payment reminders
simple Nigerian English phrasing
introductory Nigerian Pidgin translations
maintaining appropriate professional boundaries

Training approach

The adapter was trained with LoRA using the PEFT library.

The local training configuration included:

LoRA rank: 16
LoRA alpha: 32
LoRA dropout: 0.05
training epochs: 3
batch size: 1
gradient accumulation steps: 8
maximum sequence length: 512
optimizer: AdamW
CPU-compatible float32 loading
base model: Qwen/Qwen2.5-0.5B-Instruct

Evaluation status

A formal side-by-side comparison between v0.4 and v0.5 has not yet been published.

Therefore, this model card does not claim that v0.5 performs better than v0.4.

Evaluation results will be added after both adapters are tested on the same held-out benchmark and reviewed using consistent criteria.

Limitations

The training dataset is very small and unevenly distributed.

In particular:

business writing has only one example
Nigerian Pidgin has only one example
the adapter may overfit specific phrasings
responses may be inconsistent
cultural coverage is narrow
the model may hallucinate information
safety behaviour has not been independently audited
performance outside the training categories is unknown
English and Pidgin quality may vary significantly

All important outputs should be reviewed by a person.

Version history

Version	Status
v0.1	Initial experimental adapter
v0.2	Early iterative release
v0.3	Expanded experimental release
v0.4	First formally reviewed and benchmarked development version
v0.5	Reproducible dataset pipeline and corrective-example training release

Project links

GitHub: https://github.com/oluwafemidiakhoa/gaialab-naija-assistant
Model: https://huggingface.co/mgbam/gaialab-naija-adapter-v0.5
GaiaLab AI: https://www.gailabai.com

Responsible-use statement

GaiaLab Naija Assistant is an experimental research project. Users are responsible for reviewing generated content before relying on it or sending it to others.

Do not use this model to impersonate individuals, facilitate fraud, request confidential credentials, or make consequential decisions without qualified human oversight.

Author

Developed by Oluwafemi Idiakhoa under the GaiaLab AI initiative.