Downloads · 30 days
0
PeaceMmesoma-15/Igbo-qwen-finetuned
Igbo-qwen-finetuned is a machine learning model from PeaceMmesoma-15. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains a LoRA fine-tuned adapter for Qwen/Qwen2.5-0.5B-Instruct, trained to provide culturally and linguistically appropriate responses about Igbo language terms and meanings.
Downloads · 30 days
0
Access
Public
Updated Aug 14, 2026
Repo size
15.8 MB
Likes
0
Public
Click a slice to open those files.
.json11.4 MB · 72%
From the Hugging Face model README
This repository contains a LoRA fine-tuned adapter for Qwen/Qwen2.5-0.5B-Instruct, trained to provide culturally and linguistically appropriate responses about Igbo language terms and meanings.
The dataset contains 490 examples in total.
After filtering and splitting:
The examples contain Igbo terms, their meanings, and target responses intended to encourage accurate and culturally appropriate explanations.
The model was fine-tuned for 2 epochs on a Google Colab T4 GPU.
Training configuration:
The final training results were:
| Metric | Result |
|---|---|
| Training loss | 1.7721 |
| Evaluation loss | 1.5532 |
| Training time | approximately 141 seconds |
| Training examples | 439 |
| Evaluation examples | 49 |
A loss plot was generated during the experiment to monitor training and evaluation performance.
This model is intended for educational and experimental use involving Igbo language terms, meanings, and culturally informed explanations.
It can be used as a starting point for research into low-resource African-language NLP and culturally aware language models.
The model was trained on a relatively small dataset of 490 examples. Therefore, it should not be assumed to provide complete or authoritative coverage of the Igbo language or Igbo cultural knowledge.
Responses should be reviewed by fluent Igbo speakers or knowledgeable cultural experts, particularly for historical, cultural, or context-sensitive claims.
The model is a LoRA adapter and requires the corresponding base model, Qwen/Qwen2.5-0.5B-Instruct, for inference.
This project was developed as an experiment in fine-tuning a small language model for Igbo language and cultural knowledge using parameter-efficient fine-tuning with LoRA.