LLMs

This course supplements Ed Donner's Udemy course, "LLM Engineering: Master AI & Large Language Models (LLMs)," for developers working with Ubuntu 22.04'.

Info

Look at Blog for the latest remarks!

Content

Introduction

My name is Rob Bontekoe and I am attendig Ed Donner's Udemy course LLM Engineering: Master AI & Large Language Models (LLMs).

Docker logo

Logo Ed Donner's course

I work with Ubuntu 22.04 Desktop version. I asked Ed whether I could attend the course using MiniConda. He said: "Hey Rob, I haven't tested miniconda myself, but another student mentioned that he used miniconda and everything went great. I'd actually be super grateful if you could give it a whirl and let me know - then I can update the instructions with this as an approach. Thanks so much Ed."

I also prefer to use Docker, because it gives you less trouble on your system. Looking at https://docs.anaconda.com/anaconda/install/ I saw in step 4 https://docs.anaconda.com/working-with-conda/applications/docker/ the next Docker instruction:

docker run -i -t -p 8888:8888 continuumio/miniconda3 /bin/bash \
-c "/opt/conda/bin/conda install jupyter -y --quiet && mkdir \
/opt/notebooks && /opt/conda/bin/jupyter notebook \
--notebook-dir=/opt/notebooks --ip='*' --port=8888 \
--no-browser --allow-root"

Because I prefer to use docker-compose I translated the command with Gemini into a compose.yml file which I can use with docker-compose to create de container automatically.

The advantage was that I only had to restart the container and could use a one time generated api key to enter Jupyter notebooks.

version: "3.9" # Use the latest version of the Docker Compose file format

services:
  jupyter-notebook:
    image: continuumio/miniconda3
    ports:
      - "8888:8888"
    command: 
      - /bin/bash
      - "-c"
      - |
        conda install jupyter -y --quiet && \
        mkdir -p /opt/notebooks && \
        jupyter notebook \
          --notebook-dir=/opt/notebooks \
          --ip='*' \
          --port=8888 \
          --no-browser \
          --allow-root
    volumes:
      - ./notebooks:/opt/notebooks 
    tty: true
    stdin_open: true

I hope you appreciate this approach.

Rob Bontekoe

This course is licensed under the MIT License.

An MIT license is a type of software license, also known as an open-source license. It's one of the most permissive licenses available, meaning it grants users a wide range of freedoms to use, modify, and distribute the software.