---
language:
- pcm
- en
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
base_model: Qwen/Qwen3-4B
tags:
- Nigerian-Pidgin
- Naija
- Pidgin-English
- Africa
- unsloth
- fine-tuned
- qwen3
datasets:
- ahmadabdulnasir/naijaPidgin
---

# NaijaPidgin-Qwen3-4B 🇳🇬

A fine-tuned Qwen3-4B model that understands and speaks **Nigerian Pidgin English (Naija)** fluently.

## Model Description

This model was fine-tuned from `Qwen/Qwen3-4B` using [Unsloth](https://github.com/unslothai/unsloth)
with QLoRA on the [naijaPidgin dataset](https://huggingface.co/datasets/ahmadabdulnasir/naijaPidgin).

**Capabilities:**
- Conversational Pidgin English
- Pidgin ↔ English translation
- Nigerian culture, proverbs, and everyday advice
- Code-switching between Pidgin and English
- Thinking mode (Qwen3 feature) for complex questions

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ahmadabdulnasir/NaijaPidgin-Qwen3-4B")
tokenizer = AutoTokenizer.from_pretrained("ahmadabdulnasir/NaijaPidgin-Qwen3-4B")

messages = [
    {"role": "system", "content": "You are a helpful assistant that speaks Nigerian Pidgin English. /no_think"},
    {"role": "user", "content": "How you dey?"},
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256, temperature=0.7, top_p=0.8, top_k=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### With Thinking Mode

Remove `/no_think` from the system prompt to enable Qwen3's reasoning mode:

```python
messages = [
    {"role": "system", "content": "You are a helpful assistant that speaks Nigerian Pidgin English."},
    {"role": "user", "content": "If I get 50,000 naira, wetin be di best investment?"},
]
```

### With Ollama

Download the GGUF version and run locally:

```bash
ollama run ahmadabdulnasir/NaijaPidgin-Qwen3-4B
```

## Training Details

- **Base model:** Qwen/Qwen3-4B
- **Method:** QLoRA (4-bit) with Unsloth
- **LoRA rank:** 32
- **Learning rate:** 2e-4
- **Epochs:** 3
- **Hardware:** Google Colab G4 GPU (96GB VRAM)
- **Dataset:** ahmadabdulnasir/naijaPidgin

## Citation

```bibtex
@misc{naijapidgin_qwen3_2025,
  title={NaijaPidgin-Qwen3-4B},
  author={Ahmad Abdulnasir Shuaib},
  year={2025},
  url={https://huggingface.co/ahmadabdulnasir/NaijaPidgin-Qwen3-4B}
}
```