Chatbot AI

Introduction

In this repository we have done all of the data analysis and fine-tunining work and we have provided all of the deployed models and datasets resources.

Outline:

1. We installed dependencies and load the dataset from hugging face, and then fine tuned llama 3.2 1B model in Spark2.ipynb notebook.
2. We deployed the model on hugging face and also on ollama.

Future work:

1. We have create a new dataset contains the English conversations in the first dataset and also with Arabic conversations and then we shuffled them using Pandas as we did in data_preparation.ipynb notebook.
2. Soon we will train the model on the new dataset to allow users to send Arabic and English messages to our model.

Resources:

1. Ar-En version dataset on hugging face: Dataset
2. Fine-Tuned model on hugging face: Model
3. Ollama deployed model: Ollama

Contacts:

For more informations about how we fine-tuned our model I can provide you a step by step tutorial to do that, just contact me here or on my email address [email protected].