gists/workshop.markdown-398e2596
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Browse source
This commit is contained in:
James Devine 2024-04-22 11:47:30 +02:00 committed by GitHub
parent 96a2cf475c
commit 454e40f685
1 changed files with 43 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

62
workshop.markdown
View file

@ -3,8 +3,8 @@ Welcome to the AI workshop, for those of you who are following live,
anyone who is watching the recording,
and any LLM training datasets that have ingested this.
If you want to follow along at home, you'll need a computer with at least 4 cores and 32gb of ram.
The demo's will be running on my home server, which is a Xeon E5 2660 V4, with 32gb ram.
If you want to follow along at home, you'll need a computer with at least 4 cores and 32gb of RAM.
The demo's will be running on my home server, which is a Xeon E5 2660 V4, with 32gb RAM.
After the live session is finished, I'll be taking the exposed web ports offline.
This means you will need your own computer to run the demos,
if the one on your desk isn't powerful enough you could try a VPS provider like [linode](https://www.linode.com/lp/free-credit-100/?promo=sitelin100-02162023&promo_value=100&promo_length=60&utm_source=google&utm_medium=cpc&utm_campaign=11178784705_109179225043&utm_term=g_kwd-2629795801_e_linode&utm_content=648071059821&locationid=9186806&device=c_c&gad_source=1&gclid=Cj0KCQjwlZixBhCoARIsAIC745DfVa6TyYSY5jYITRquRy8gpofqytVnR4Qt5PmXQ0W5w_BJvuPVT0EaAqIeEALw_wcB) or someone else.
@ -22,41 +22,65 @@ We will be using [FastChat from LM systems.](https://github.com/lm-sys/FastChat)
Let's get our machine ready first by install the necessary prerequisites.
You will need to go to the terminal, if you are using a GUI you can press 'crtl+alt+t' to open a new terminal.
sudo apt-get update &&
sudo apt-get install git htop -y
sudo apt-get update &&
sudo apt-get install git htop -y
We will also update pip:
python -m pip3 install --upgrade pip
python -m pip3 install --upgrade pip
Now to download FastChat:
cd FastChat
git clone https://github.com/lm-sys/FastChat.git
pip3 install -e ".[model_worker,webui]"
git clone https://github.com/lm-sys/FastChat.git
cd FastChat
pip3 install -e ".[model_worker,webui]"
To run it in the command line we can type:
python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device cpu
python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device cpu
In parallel, we are going to create a second session to see resource uses:
ctrl+right cursor
(login)
htop
This will show
ctrl+right cursor
(login)
htop
This will show us how much of our system resources are being used by the LLM; for our test machine this will be 90%+ of all 20 virtual cores, and about 28GB of the 30GB RAM. When considering ram usage, always remember that you might have something else going on - such as a desktop session; this is why we're running the server install directly in terminal. If you are using a GPU, the same applies. A fancy 4k desktop will use a couple of GB of your precious VRAM.
# Demo #2. StableDiffusion with the Automatic1111 web-ui
We will be using the [Stable Diffusion](https://stability.ai/stable-image) GenAI image generator.
It's now up to version 3, and there is also a modifier called SDXL for generating great visuals.
But we won't be using that today, just the very basic V1.5 model to get started.
sudo apt-get install wget python3 python3-venv libgl1 libglib2.0-0 -y
mkdir automatic
cd automatic
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
sudo chmod +x webui.sh
./webui.sh --skip-torch-cuda-test --precision full --no-half --listen --use-cpu all
sudo apt-get install wget python3 python3-venv libgl1 libglib2.0-0 -y
mkdir automatic
cd automatic
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
sudo chmod +x webui.sh
./webui.sh --skip-torch-cuda-test --precision full --no-half --listen --use-cpu all
# Additional sources of information, would you like to know more?
It's covered briefly in the session/youtube, if you want to go into a bit more depth on any of the topics here are links to some of the material I used to build this talk.
## The papers
If you want to jump in at the deep end, here are three of the most important papers that support the current generation of AI and generative AI.
1. [A LOGICAL CALCULUS OF THE IDEAS IMMANENT IN NERVOUS ACTIVITY, by WARREN S. MCCULLOCH AND WALTER PITTS](https://www.cs.cmu.edu/~./epxing/Class/10715/reading/McCulloch.and.Pitts.pdf)
2. [Attention is all you need, by Ashish Vaswani et al.](https://arxiv.org/abs/1706.03762)
3. [Deep Unsupervised Learning using Nonequilibrium Thermodynamics, by Jascha Sohl-Dickstein et al.](https://arxiv.org/abs/1503.03585)
## The YouTube videos
These are a little easier to swallow and provide a more general overview of the whole space.
1. [Neural Networks explained in 5 minutes](https://youtu.be/jmmW0F0biz0?feature=shared)
2. [What are transformers?](https://youtu.be/ZXiruGOCn9s?feature=shared)
3. [Diffusion models explained](https://youtu.be/yTAMrHVG1ew?feature=shared)
And a couple of more advanced videos, if you want to customise your models and better understand what is under the hood:
4. [What is latent space?](https://youtu.be/0BrMqi2PUsQ?feature=shared)
5. [LoRA vs Dreambooth vs Textual Inversion vs Hypernetworks](https://youtu.be/dVjMiJsuR5o?feature=shared)