--- title: "AI Notebooks - Tutoriel - Fine-tuner LLaMA 2 (EN)" description: "Fine-tuner LLaMA 2 sur votre propre dataset en utilisant un seul GPU, QLoRA et AI Notebooks afin d'exploiter pleinement son potentiel" url: https://docs.ovhcloud.com/fr/guides/public-cloud/ai-machine-learning/ai-notebooks-tuto-fine-tune-llama-v2 lang: fr lastUpdated: 2023-07-25 --- # AI Notebooks - Tutoriel - Fine-tuner LLaMA 2 (EN) On July 18, 2023, [Meta](https://about.meta.com/) released [LLaMA 2](https://ai.meta.com/llama/), the latest version of their open-source Large Language Model (LLM). Trained between January 2023 and July 2023 on 2 trillion tokens, LLaMA 2 outperforms other LLMs on many benchmarks, including reasoning, coding, proficiency, and knowledge tests. This release comes in different flavors, with parameter sizes of 7B, 13B, and a mind-blowing 70B. Models are intended for free for both commercial and research use in English. ## Objective The purpose of this tutorial is to show you how it is possible to fine-tune LLaMA 2 models using [OVHcloud AI Notebooks](https://www.ovhcloud.com/fr/public-cloud/ai-notebooks/) and a single GPU. This allows you to retrain the model to suit your needs, using your own dataset. We will use [QLoRA](https://arxiv.org/abs/2305.14314), a highly efficient LLM fine-tuning technique. ## Requirements - An AI Notebooks project created inside a [Public Cloud project](https://www.ovhcloud.com/fr/public-cloud/) in your OVHcloud account - A user for AI Notebooks To access LLaMA 2 models, you will also need to follow the requirements indicated in the notebook. *** ### OVHcloud Control Panel Access - **Direct link:** Public Cloud Projects - **Navigation path:** Public Cloud > Select your project *** ## Instructions You can launch the notebook from the OVHcloud Control Panel or via the ovhai [CLI](/fr/guides/public-cloud/ai-machine-learning/ai-cli-run-notebook.md) . ### Launching a Jupyter notebook with "Conda" via UI (Control Panel) To launch your notebook from the OVHcloud Control Panel , refer to the following steps. #### Code editor Choose the `Jupyterlab` code editor. #### Framework In this tutorial, the `conda` framework is used. #### Resources Using at least one **GPU is mandatory**, since fine-tuning LLMs is an intensive task. ### Launching a Jupyter notebook with "conda" via CLI _If you do not use our CLI yet, follow [this guide](/fr/guides/public-cloud/ai-machine-learning/ai-cli-install-client.md) to install it._ If you want to launch your notebook with the OVHcloud AI CLI, choose the `jupyterlab` editor and the `conda` framework. To access the different versions of `conda` available, run the following command: ```console ovhai capabilities framework get conda -o yaml ``` :::info If you do not specify a version, your notebook starts with the default version of `conda`. ::: You will also need to choose the number of GPUs to use in your notebook using ``. To launch your notebook, run the following command: ```console ovhai notebook run conda jupyterlab \ --name \ --framework-version \ --gpu ``` You can then reach your notebook’s URL once the notebook is running. ### Accessing the notebooks Once our [AI examples repository](https://github.com/ovh/ai-training-examples/) has been cloned in your environment, find the fine-tuning notebook tutorial by following this path: `ai-training-examples` > `notebooks` > `natural-language-processing` > `llm` > `miniconda` > `llama2-fine-tuning` > `llama_2_finetuning.ipynb`. Direct link to the notebook can be found [here](https://github.com/ovh/ai-training-examples/blob/main/notebooks/natural-language-processing/llm/miniconda/llama2-fine-tuning/llama_2_finetuning.ipynb). ## Going further Don't forget to keep an eye on our upcoming tutorials, where we will be deploying our fine-tuned LLaMA model on [AI Deploy](https://www.ovhcloud.com/fr/public-cloud/ai-deploy/) for inference! In the meantime, we invite you to take a look at our other NLP tutorials: - [Analyse sentiments on Tweets](/fr/guides/public-cloud/ai-machine-learning/ai-notebooks-hugging-face-sentiment-analysis.md) - [Create a Spam classifier](/fr/guides/public-cloud/ai-machine-learning/ai-notebooks-spam-classifier.md) - [Discover speech to text powers and use them to generate video subtitles, meeting scripts and summaries](/fr/guides/public-cloud/ai-machine-learning/ai-notebooks-speech-to-text-recognition.md) If you need training or technical assistance to implement our solutions, contact your sales representative or click on [this link](https://www.ovhcloud.com/fr/professional-services/) to get a quote and ask our Professional Services experts for a custom analysis of your project. ## Feedback Please send us your questions, feedback and suggestions to improve the service: - On the OVHcloud [Discord server](https://discord.gg/ovhcloud)