Install Llama 2, the Meta Open Source and Commercializable AI that competes with Chat GPT for use with Python and Docker (with GPU access)

by
Tiempo de lectura: 3 minutos

Hello, today we will see how we can install and download llama 2, the Meta AI that competes with chatgpt 3.5. For this, I have created a Docker Compose that will help us set up the environment.

The first thing we need to do is go to the llama 2 page and request a version from their own website https://ai.meta.com/llama/

Now it will ask for an email address, I recommend using a university or research email account to get the approval as quickly as possible:

Next, you will receive an email with installation instructions.

To get started, we first need to download the Llama 2 environment without the model. For this, we go to their GitHub and clone it:

https://github.com/facebookresearch/llama

Once downloaded, we can either install it on our machine or use a Docker Compose.

I will create a Docker Compose that you can use to install this AI:

  • Create a folder named ‘app’ at the root of the project
  • Now create another folder named ‘Dockerfile’ where we will add our custom environment configuration file.

Create a file called ‘container_python’ inside Dockerfile (Dockerfile/container_python) and add this content:

# syntax=docker/dockerfile:1
#FROM python:3.11.3
FROM python:3.8

#WORKDIR /app

#-y is for when it gives an error of yes
RUN apt-get update -y
RUN apt install python3-pip -y
RUN pip install --upgrade pip
# Run a command to keep the container running
CMD tail -f /dev/null

Now create a file at the root named docker-compose.yml

version: "3.1"

services:

  llama_ia_python:
      build:
        context: ./Dockerfile
        dockerfile: container_python
      restart: unless-stopped
      container_name: llama_ia_python
      working_dir: /app
      volumes:
        - ./app:/app

With this, our environment is now set up.

Now, we have to launch the container with the command:

docker compose up -d

This will leave the container running in the background, and we can execute our commands. I recommend accessing the console directly from Docker:

docker exec -it llama_ia_python bash

This will open the console for us.

The first thing we need to do is navigate to the llama repository:

cd llama-main

And run download.sh to download the necessary models.

./download.sh

Now it will ask for the installation URL, this URL is received from the email (“When asked for your unique custom URL, please insert the following:”), copy it and paste it.

It will now ask us which models we want to download, if we want all of them, press enter.

It will start downloading the models:

Once the models are downloaded, I recommend saving them separately. They are in the folders:

Since it only allows downloading for 24 hours and 5 times.

Once the models are downloaded, we can install llama:

pip install -e .

Now, to check if it works, we need to use this command:

torchrun --nproc_per_node 1 example_text_completion.py \
    --ckpt_dir llama-2-7b/ \
    --tokenizer_path tokenizer.model \
    --max_seq_len 128 --max_batch_size 4

*Note: If you use Docker, make sure it can access the GPU, otherwise this service will not work. If it doesn’t work with Docker Compose, you can try running it locally.

Post Views: 26

Leave a Comment