{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "XB3s11WZoi3s" }, "source": [ "# πFine-tuning a pre-trained machine translation model\n", "\n", "Machine translation has come a long way in recent years, and pre-trained models such as those based on transformer architectures have shown impressive performance on a wide range of translation tasks. However, to achieve the best results for a specific use case, it is often necessary to fine-tune the model on domain-specific data. " ] }, { "cell_type": "markdown", "metadata": { "id": "2f0xpA-pqB2k" }, "source": [ "" ] }, { "cell_type": "markdown", "metadata": { "id": "OU1n0cYkVaiu" }, "source": [ "## Introduction\n", "\n", "In this tutorial, you will learn how to fine-tune a pre-trained model for a machine translation task. It will walk you through the following steps:\n", "\n", "- π Download the dataset and put it in the argilla space.\n", "- π£ Preprocess the dataset for the fine-tuning. \n", "- π Fine-tune the dataset into the model and train it. \n", "- π Evaluate the model.\n", "\n", "Let's get started!" ] }, { "cell_type": "markdown", "metadata": { "id": "wg967G1LVaiu" }, "source": [ "## Running Argilla\n", "\n", "For this tutorial, you will need to have an Argilla server running. There are two main options for deploying and running Argilla:\n", "\n", "1. [Deploy Argilla on Hugging Face Spaces](https://huggingface.co/docs/hub/spaces-sdks-docker-argilla): This is the fastest option and the recommended choice for connecting to external notebooks (e.g., Google Colab) if you have an account on Hugging Face.\n", "\n", "2. [Launch Argilla using Argilla's quickstart Docker image](../../getting_started/quickstart.ipynb): This is the recommended option if you want Argilla running on your local machine. Note that this option will only let you run the tutorial locally and not with an external notebook service.\n", "\n", "For more information on deployment options, please check the Deployment section of the documentation.\n", "\n", "