LLM_Fine-Tunning_Amharic

About

This GitHub repository contains notebooks that use the Amharic news category classification dataset to fine-tune various models for a text classification task.

The fine-tuned model classifies a given Amharic news article into one of the following six categories:

• Local News
• Entertainment
• Sports
• Business
• International News
• Politics

How to Use

Clone the Repository

First, clone this repository to your local machine:

bash

git clone https://github.com/10Academy-chortB/LLM_Fine-Tunning_Amharic
cd LLM_Fine-Tunning_Amharic

Download the Model from Hugging Face

Next, obtain the pre-trained model from Hugging Face:

bash

git clone https://huggingface.co/Yohanes213/Amharic_news_classification

Run the Frontend

To launch the frontend, execute the following command:

bash

npm run

Reference

• Andersland, Mike. "Llama-2-Amharic: LLMs for Low Resource Languages." Medium, Dec. 2023 Medium
• "amharic-news-category-classification"(https://paperswithcode.com/dataset/an-amharic-news-text-classification-dataset)