[0:00] I'm running something called private
ai. It's kind of like chat GPT,
[0:03] except it's not. Everything about it
is running right here on my computer.
[0:07] Am I even connected to the internet?
[0:08] This is private contained and my data
isn't being shared with some random
[0:12] company. So in this video I
want to do two things. First,
[0:15] I want to show you how to set this up.
[0:16] It is ridiculously easy and fast to run
your own AI on your laptop computer or
[0:21] whatever. It's this is free, it's amazing.
[0:23] It'll take you about five minutes and
if you stick around until the end,
[0:26] I want to show you something even
crazier, a bit more advanced.
[0:28] I'll show you how you can connect
your knowledge base, your notes,
[0:31] your documents,
[0:32] your journal entries to your own
private GPT and then ask it questions
[0:37] about your stuff. And then second,
[0:38] I want to talk about how private AI is
helping us in the area we need help Most.
[0:42] Our jobs, you may not know this,
[0:44] but not everyone can use chat GBT
or something like it at their job.
[0:47] Their companies won't let them mainly
because of privacy and security reasons,
[0:51] but if they could run their own
private ai, that's a different story.
[0:54] That's a whole different ballgame and
VMware is a big reason. This is possible.
[0:58] They're the sponsor of this video and
they're enabling some amazing things that
[1:01] companies can do on-Prem in their
own data center to run their own ai.
[1:05] And it's not just the cloud man,
it's like in your data center.
[1:07] The stuff they're doing is crazy. We're
going to talk about it here in a bit,
[1:10] but tell you what, go ahead and do
this. There's a link in the description.
[1:13] Just go ahead and open it and take a
little glimpse at what they're doing.
[1:16] We're going to dive deeper,
[1:16] so just go ahead and have it open right
in your second monitor or something or
[1:20] on the side or minimize. I
don't know what you're doing.
[1:22] I dunno how many monitors you
have. You have three Actually, Bob,
[1:25] I can see before we get started,
I have to show you this.
[1:27] You can run your own private ai. That's
kind of uncensored. I watch this,
[1:34] So yeah, please don't do
this to destroy me. Also,
[1:37] make sure you're paying attention
at the end of this video,
[1:39] I'm doing a quiz and if you're one of
the first five people to get a hundred
[1:42] percent on this quiz, you're getting
some free coffee network. Chuck Coffee.
[1:46] So take some notes,
study up. Let's do this
[1:51] now real quick, before we install a
private local AI model on your computer,
[1:55] what does it even mean? What's
an AI model? At its core,
[1:58] an AI model is simply an artificial
intelligence pre-trained on data we
[2:02] provided. One you may have
heard of is open AI's Chat GBT,
[2:05] but it's not the only one out
there. Let's take a field trip.
[2:08] We're going to go to a website
called hugging face.co.
[2:11] Just an incredible brand
name. I love it so much.
[2:14] This is an entire community dedicated
to providing and sharing AI models and
[2:18] there are a ton. You're about
to have your mind blown. Ready?
[2:21] I'm going to click on models up here. Do
you see that number? 505,000 AI models.
[2:26] Many of these are open and free
for you to use and pre-trained,
[2:30] which is kind of a crazy
thing. Let me show you this.
[2:32] We're going to search for
a model named Llama two,
[2:35] one of the most popular models out
there. We'll do LAMA two seven B. Again,
[2:39] I love the branding.
[2:40] LAMA two is an AI model known as
an LLM or large language model,
[2:45] open AI's Chat. GPT is
also an LLM. Now this LLM,
[2:48] this pre-trained AI
model was made by meda,
[2:51] AKA Facebook and what
they did to pre-train.
[2:54] This model is kind of insane and the fact
that we're about to download this and
[2:58] use it even crazier, check this out
if you scroll down just a little bit,
[3:01] here we go. Training data.
[3:03] It was trained by over 2 trillion
tokens of data from publicly available
[3:07] sources. Instruction data sets over
a million human annotated examples,
[3:11] data freshness. We're talking
in July, 2023. I love that term.
[3:15] Data freshness and getting
the data was just step one.
[3:18] Step two is insane because this
is where the training happens.
[3:21] Mata to train this model put together
what's called a super cluster.
[3:25] It already sounds cool, right?
This sucker is over 6,000 GPUs.
[3:29] It took 1.7 million GPU hours to
train this model and it's estimated it
[3:34] costs around $20 million to train
it and now made is just like,
[3:39] here you go kid. Download this
incredibly powerful thing.
[3:43] I don't want to call it a being
yet. I'm not ready for that,
[3:46] but this intelligent source of information
that you can just download on your
[3:50] laptop and ask it questions,
[3:51] no internet required and this is just
one of the many models we could download.
[3:55] They have special models like
text to speech, image to image.
[3:58] They even have uncensored ones. They have
an uncensored version of a llama too.
[4:02] This guy George Sung,
[4:04] took this model and fine tuned
it with a pretty hefty GPU,
[4:08] took him 19 hours and made it to where
you could pretty much ask this thing.
[4:11] Anything you wanted, whatever
question comes to mind,
[4:14] it's not going to hold back. Okay,
[4:16] so how did we get this fine tuned
model onto your computer? Well,
[4:19] actually I should warn you, this
involves quite a bit of llamas,
[4:22] more than you would expect. Our
journey starts at a tool called O Lama.
[4:26] Let's go ahead and take a field
trip out there real quick.
[4:28] We'll go to O lama.ai. All we'll have
to do is install this little guy, Mr.
[4:32] Alama,
[4:32] and then we can run a ton of different
LLMs Llama two Code Llama told you lots
[4:37] of llamas and there's others that are
pretty fun like Llama two Uncensored or
[4:41] Llamas. Tdrl. I'll show you in a second.
But first, what do we install alama on?
[4:46] We can see right down here that we
have it available on macOS and Linux,
[4:49] but oh bummer, windows coming soon.
[4:52] It's okay because we've got WSL,
the Windows subsystem for Linux,
[4:56] which is now really easy to set up.
[4:58] So we'll go ahead and click on
download right here from os.
[5:01] You'll just simply download this
and install like one of your regular
[5:04] applications for Linux.
We'll click on this.
[5:07] We got to fun curl command that will
copy and paste now because we're going to
[5:09] install WSL on Windows. This will
be the same step. So Mac OS folks,
[5:15] go ahead and just run that installer.
Linux and Windows folks, let's keep going.
[5:19] Now, if you're on Windows,
[5:20] all you have to do now to get WSL
installed is launch your Windows terminal.
[5:23] Just go to your search bar and search
for terminal and with one command it'll
[5:27] just happen. It used to be so much
harder, which is WSL dash dash install.
[5:32] It'll go through a few steps.
It'll install Ubuntu as default.
[5:35] I'll go ahead and let that do
that. And boom, just like that.
[5:39] I've got Ubuntu 22 0 4 3 lts installed
and I'm actually inside of it right
[5:44] now. So now at this point, Linux
and Windows folks, we converged.
[5:47] We're on the same path.
Let's install alama.
[5:49] I'm going to copy that curl
command that alama gave us,
[5:52] jump back into my terminal, paste
that in there and press enter.
[5:55] Fingers crossed, everything should be
great. Like the way it is right now,
[5:59] it'll ask for my pseudo password and
that was it. Oh, LAMA is now installed.
[6:04] Now this will directly apply to
Linux people and Windows people.
[6:07] See right here where it says Nvidia
GPU installed. If you have that,
[6:10] you're going to have a better time
than other people who don't have that.
[6:13] I'll show you here in a second.
If you don't have it, that's fine.
[6:15] We'll keep going. Now let's run an
LLM. We'll start with llama two.
[6:18] So we'll simply type in, oh Lama run,
[6:22] and then we'll pick one llama
two and that's it. Ready,
[6:26] set go. It's going to pull the manifest.
[6:28] It'll then start pulling down
and downloading Llama two.
[6:31] And I want you to just realize this,
that powerful LAMA two pre-training,
[6:34] we talked about all the money and
hours spent. That's how big it is.
[6:38] This is the 7 billion
parameter model or the seven B.
[6:42] It's pretty powerful and we're about to
literally have this in the palm of our
[6:45] hands in like 3, 2, 1. Oh,
I thought I had it. Anyways,
[6:49] it's almost done. And boom, it's done.
[6:52] We've got a nice success message
right here and it's ready for us.
[6:56] We can ask you anything.
Let's try what is a pug?
[6:59] Now the reason this is going
so fast, just like a side note,
[7:01] is that I'm running A GPU
and AI models love GPUs.
[7:05] So lemme just show you real quick.
[7:06] I did install alama on a Linux
virtual machine and I'll just demo the
[7:10] performance for you real quick. By the
way, if you're running a Mac with an M1,
[7:13] M two or M three processor, it actually
works great. I forgot to install it.
[7:17] I got to install it real quick and
I'll ask you that same question.
[7:19] What is a pug? It's going to
take a minute, it'll still work,
[7:22] but it's going to be slower on CPUs and
there it goes. It didn't take too long,
[7:25] but notice it is a bit slower.
[7:27] Now if you're running WSL and you know
have an Nvidia GPU and it didn't show up,
[7:31] I'll show you in a minute how you can
get those drivers installed. But anyways,
[7:34] just sit back for a minute,
[7:35] sip your coffee and think
about how powerful this is.
[7:38] The tinfoil hat version of me
stinking loves this because let's say
[7:43] the zombie apocalypse happens, right?
The grid goes down, things are crazy,
[7:47] but as long as I have my
laptop and a solar panel,
[7:51] I still have AI and it can help
me survive the zombie apocalypse.
[7:55] Let's actually see how that would
work. It gives me next steps.
[7:58] I could have it help me with the water
filtration system. This is just cool,
[8:01] right? It's amazing. But can
I show you something funny?
[8:04] You may have caught this
earlier. Who is network? Chuck?
[8:09] What? Dude, I've always
wanted to be Rick Grimes.
[8:14] That is so fun, but seriously,
it kind of hallucinated there.
[8:17] It didn't have the correct information.
[8:19] It's so funny how it mixed the
zombie apocalypse prompt with me.
[8:23] I love that so much. Let's try
a different model. I'll say bye.
[8:27] I'll try a really fun one
called mytral. And by the way,
[8:30] if you want to know which ones you
can run with Llama, which LLMs,
[8:33] they get a page for their models right
here and all the ones you can run,
[8:36] including llama two,
uncensored Wizard Math.
[8:39] I might give that to my kids
actually. Let's see what it says.
[8:41] Now who is Network Chuck?
[8:45] Now my name is not Chuck Davis and my
YouTube channel is not called Network
[8:50] Chuck on Tech.
[8:50] So clearly the data this thing was trained
on is either not up to date or just
[8:54] plain wrong. So now the question is cool,
[8:57] we've got this local private ai,
this LLM, that's super powerful,
[9:02] but how do we teach it the
correct information for us?
[9:05] How can I teach it to know
that I'm network Chuck,
Chuck Keith, not Chuck Davis,
[9:08] and my channel is called Network Chuck.
[9:09] Or maybe I'm a business and I want it
to know more than just what's publicly
[9:13] available because sure, right
now if you downloaded this lm,
[9:16] you could probably use it in your job,
[9:17] but you can only go so far without it
knowing more about your job. For example,
[9:22] maybe you're on a help desk.
[9:23] Imagine if you could take your help
desk's knowledge base, your IT procedures,
[9:27] your documentation. Not only that,
[9:29] but maybe you have a database
of closed tickets, open tickets.
[9:31] If you could take all that data and
feed it to this LLM and then ask it
[9:35] questions about all of
that, that would be crazy.
[9:38] Or maybe you wanted to help troubleshoot
code that your company's written.
[9:41] You could even make this LM
public facing for your customers.
[9:44] You feed information about your product
and the customer could interact with
[9:47] that chat bot you make.
[9:49] Maybe this is all possible with a process
called fine tuning where we can train
[9:53] this AI on our own proprietary
secret private stuff about our
[9:58] company or maybe our lives or
whatever you want to use it for,
[10:00] whatever use case is,
[10:01] and this is fantastic because maybe before
you couldn't use a public LLM because
[10:05] you weren't allowed to share your
company's data with that LLM,
[10:08] whether it's compliance reasons or you
just simply didn't want to share that
[10:10] data because it's secret.
Whatever the case,
[10:12] it's possible now because
this AI is private,
[10:15] it's local and whatever
data you feed to it,
[10:18] it's going to stay right there in a
company. It's not leaving the door.
[10:20] That idea just makes me so excited
because I think it is the future of AI and
[10:24] how companies and individuals
will approach it. It's
going to be more private.
[10:28] Back to our question though,
fine tuning, that sounds cool.
[10:31] Training and AI on your own
data, but how does that work?
[10:34] Because as we saw before with
pre-training a model with mata,
[10:38] it took them 6,000 GPUs
over 1.7 million GPU hours.
[10:42] Do we have to have this massive
data center to make this happen? No.
[10:46] Check this out, and this is such a fun
example, VMware, they asked chat GPT,
[10:50] what's the latest version
of VMware vSphere?
[10:52] Now the latest chat GPT
knew about was vSphere 7.0,
[10:55] but that wasn't helpful to VMware because
their latest version they were working
[10:58] on chat hadn't been released yet.
[10:59] So it wasn't public knowledge
was vSphere eight update too.
[11:02] And they wanted information like this
internal information not yet released to
[11:06] the public.
[11:07] They wanted this to be available to
their internal team so they could ask
[11:10] something like chat GBT, Hey, what's
the latest version of vSphere?
[11:14] And they could answer correctly.
[11:15] So to do what VMware is trying to do
to fine tune a model or train it on new
[11:19] data, it does require a lot. First of all,
[11:22] you would need some
hardware servers with GPUs.
[11:24] Then you would also need a bunch of
tools and libraries and SDKs like PyTorch
[11:29] and TensorFlow, pandas, MPI side
kit, learn transformers and fast ai.
[11:33] The list goes on.
[11:34] You need lots of tools and resources
in order to fine tune an LLM.
[11:37] That's why I'm a massive fan of
what VMware is doing right here.
[11:40] They have something called the
VMware private AI with Nvidia,
[11:44] the gajillion things I just listed
off. They include in one package,
[11:49] one combo meal, a recipe of
ai, fine tuning goodness.
[11:53] So as a company it becomes a bit easier
to do this stuff yourself locally.
[11:57] For the system engineer you have on
staff who knows VMware and loves it,
[12:00] they could do this stuff,
[12:01] they could implement this and the data
scientists they have on staff that will
[12:04] actually do some of the fine tuning,
all the tools are right there.
[12:07] So here's what it looks like to fine tune
and we're going to kind of peek behind
[12:10] the curtain at what a data
scientist actually does.
[12:12] So first we have the infrastructure
and we start here in vSphere, VMware.
[12:17] Now if you don't know what vSphere
is or VMware, think virtual machines,
[12:20] you got one big physical server. The
hardware, the stuff you can feel,
[12:23] touch and smell. You haven't smelled
the server, I dunno what you're doing.
[12:26] And instead of installing one operating
system on them like Windows or Linux,
[12:29] you install VMware's, EA XI,
[12:31] which will then allow you to virtualize
or create a bunch of additional virtual
[12:35] computers. So instead of one computer,
[12:37] you've got a bunch of computers all
using the same hardware resources.
[12:40] And that's what we have right here.
One of those virtual computers,
[12:43] a virtual machine.
[12:44] This by the way is one of their special
deep learning VMs that has all the tools
[12:49] I mentioned and many, many more
pre-installed, ready to go.
[12:53] Everything a data scientist could love.
[12:55] It's kind of like a surgeon walking in
to do some surgery and like their doctor
[12:59] assistants or whatever have
prepared all their tools.
[13:01] It's all in the tray laid out
nice and neat to the surgeon.
[13:04] All he has to do is walk
in and just go scalpel.
[13:08] That's what we're doing
here for the data scientist.
[13:10] Now talking more about hardware,
[13:11] this guy has a couple Nvidia GPUs assigned
to it or pass through to it through
[13:16] a technology called PCIE Passthrough.
These are some beefy GPUs.
[13:20] I notice they are V GPU for virtual GPU
similar to what you do with the CPU,
[13:25] cutting up the PU and assigning some
of that to a virtual CPU on a virtual
[13:29] machine. So here we are in data scientists
world. This is a Jupiter notebook,
[13:33] a common tool used by a data scientist,
[13:35] and what you're going to see here is a
lot of code that they're using to prepare
[13:37] the data,
[13:38] specifically the data that they're
going to train or fine tune the existing
[13:42] model on. Now we're not
going to dive deep on that,
[13:44] but I do want you to see
this, check this out.
[13:45] A lot of this code is all about getting
the data ready. So in VMware's case,
[13:48] it might be a bunch of the knowledge
base product documentation and they're
[13:51] getting it ready to be fed to the LLM.
And here's what I wanted you to see.
[13:55] Here's the dataset that we're training
this model on. We're fine tuning.
[13:59] We only have 9,800 examples that we're
giving it or 9,800 new prompts or
[14:04] pieces of data. And that
data might look like this,
[14:06] like a simple question or a prompt and
then we feed it the correct answer and
[14:11] that's how we essentially
train ai. But again,
[14:14] we're only giving it 9,800 examples,
[14:16] which is not a lot at all and is
extremely small compared to how the
[14:20] model was originally trained.
[14:22] And I point that out to say that we're
not going to need a ton of hardware or a
[14:25] ton of resources to fine tune this model.
[14:28] We won't need the 6,000 GPUs we needed
for MATA to originally create this model.
[14:32] We're just adding to it,
[14:33] changing some things or fine tuning it
to what our use case is and looking at
[14:37] what actually will be changed
when we run this and we train it,
[14:41] we're only changing 65 million parameters,
which sounds like a lot, right?
[14:46] But not in the grand scheme of things
of like a 7 billion parameter model.
[14:49] We're only changing 0.93% of the model.
[14:52] And then we can actually
run our fine tuning,
[14:54] which this is a specific technique in
fine tuning called prompt tuning where we
[14:58] simply feed up additional prompts with
answers to change how it'll react to
[15:02] people asking you questions.
[15:03] This process will take three to four
minutes to fine tune it because again,
[15:06] we're not changing a lot and that is
just so super powerful and I think VMware
[15:10] is leading the charge with private ai.
[15:12] VMware and Nvidia take all the guesswork
out of getting things set up to fine
[15:17] tune an LLM. They've
got deep learning VMs,
[15:19] which are insane VMs that
come pre-installed with
everything you could want
[15:23] everything a data scientist
would need to find tune an LLM.
[15:26] Then Nvidia has an entire suite
of tools sensor around their GPUs,
[15:29] taking advantage of some really exciting
things to help you fine tune your lms.
[15:33] Now there's one thing I didn't talk about
because I wanted to save it for last.
[15:36] For right now it's this right
here, this vector database,
[15:39] post gray SQL box here.
[15:42] This is something called rag and it's
what we're about to do with our own
[15:46] personal GPT here in a bit. Retrieval,
augment the generation. So scenario,
[15:51] let's say you have a database of
product information, internal docs,
[15:54] whatever it is, and you haven't fine
tuned your LLM on this just yet.
[15:58] So it doesn't know about it. You
don't have to do that with rag.
[16:01] You can connect your LLM to
this database of information,
[16:05] this knowledge base and
give it these instructions.
[16:08] Say whenever I ask you a question about
any of the things in this database,
[16:11] before you answer, consult the database,
[16:13] go look at it and make sure
what you're saying is accurate.
[16:16] We're not retraining the LLM, we're
just saying, Hey, before you answer,
[16:20] go check real quick in this database to
make sure it's accurate to make sure you
[16:23] got your stuff right.
Isn't that cool? So yes,
[16:25] fine tuning is cool and training
an LLM on your own data is awesome,
[16:29] but in between those
moments of fine tuning,
[16:31] you can have rag set up where
it can consult your database,
[16:34] your internal documentation and give
correct answers based on what you have in
[16:38] that database. That is so stinking cool.
[16:40] So with VMware private AI
foundation with nvidia,
[16:43] they have those tools baked right in
to where it just kind of works for what
[16:47] would otherwise be a very complex setup.
And by the way, this whole rag thing,
[16:51] like I said earlier,
we're about to do this,
[16:53] I actually connected a lot of my notes
and journal entries to a private GPT
[16:58] using RAG and I was able to talk
with it about me asking it about my
[17:03] journal entries and answering questions
about my past. That's so powerful. Now,
[17:07] before we move on,
[17:08] I just want to highlight the fact that
Nvidia with their Nvidia AI enterprise
[17:12] gives you some amazing and fantastic
tools to pull the LLM of your choice and
[17:17] then fine tune and customize and deploy
that LLM. It's all built in right here.
[17:21] So VMware Cloud Foundation,
[17:22] they provide the robust infrastructure
and NVIDIA provides all the amazing AI
[17:26] tools you need to develop
and deploy these custom LLMs.
[17:29] Now it's not just Nvidia, they're
partnering with Intel as well.
[17:31] So VMware is covering all the
tools that admins care about.
[17:34] And then for the data
scientists, this is for you.
[17:36] Intel's got your back data analytics,
[17:38] generative AI and deep learning tools
and some classic ML or machine learning.
[17:42] And they're also working with IBM, all
you IBM fans. You can do this too. Again,
[17:46] VMware has the admin's back. But
for the data scientist, Watson,
[17:49] one of the first AI things I ever
heard about Red Hat and OpenShift,
[17:52] and I love this because what VMware
is doing is all about choice.
[17:55] If you want to run your own
local private ai, you can.
[17:58] You're not just stuck with one of the
big guys out there and you can choose to
[18:00] run it with Nvidia and VMware,
Intel and VMware, IBM and VMware.
[18:04] You got options. So there's
nothing stopping you.
[18:06] It's not for some of the bonus section
of this video and that's how to run your
[18:09] own private GPT with your own
knowledge base. Now, fair warning,
[18:14] it is a bit more advanced,
but if you stick with me,
[18:16] you should be able to get this up and
running. So take one more sip of coffee.
[18:20] Let's get this going. Now, first of
all, this will not be using a lama.
[18:23] This will be a separate project
called Private GPT. Now disclaimer,
[18:26] this is kind of hard to do.
Unlike VMware private ai,
[18:29] which they do it all for you,
[18:30] it's a complete solution for companies
to run their own private local ai.
[18:34] What I'm about to show you is not that
at all. No affiliation with VMware.
[18:37] It's a free side project.
[18:39] You can try just to get a little taste
of what running your own private GPT with
[18:44] rag tastes like. Did I do
that right? I don't know.
[18:47] Now L Martinez has a great doc on
how to install this. It's a lot,
[18:51] but you can do it. And if
you just want a quick start,
[18:53] he does have a few lines of code for
Linux and Mac users. Fair warning,
[18:57] this is CPU only. You can't really
take advantage of RAG without A GPU,
[19:00] which is what I wanted to do. So
here's my very specific scenario.
[19:03] I've got a Windows PC with an
NVIDIA 40 90. How do I run this?
[19:06] Linux-based project. WSL, and I'm so
thankful to this guy Emelia Lance a lot.
[19:11] He put an entire guide
together of how to set this up.
[19:14] I'm not going to walk you through every
step because he already did that link
[19:17] below, but I seriously need to buy
this guy a coffee. How do I do that?
[19:20] I don't know, Emil, if you're
watching this, reach out to me.
[19:22] I'll send you some coffee. So anyways,
[19:24] I went through every step from installing
all the prereqs to installing NVIDIA
[19:27] drivers and using poetry to handle
dependencies, which poetry is pretty cool.
[19:31] I landed here.
[19:32] I've got a private local working private
GPT that I can access through my web
[19:36] browser and it's using my GPU,
which is pretty cool. Now,
[19:38] first I try a simple document upload,
[19:40] got this VMware article that details
a lot of what we talked about in this
[19:43] video. I upload it and I start asking
you questions about this article.
[19:46] I tried something specific like show me
something about VMware AI market growth.
[19:50] Bam, it figured it out,
it told me. Then I'm like,
[19:52] what's the coolest thing
about VMware private ai?
[19:55] It told me I'm sitting here chatting
with a document, but then I'm like,
[19:58] let's try something bigger. I
want to chat with my journals.
[20:00] I've got a ton of journals on markdown
format and I want to ask you questions
[20:03] about me. Now this specific step
is not covered in the article.
[20:06] So here's how you do it. First,
[20:07] you'll want to grab your
folder of whatever documents
you want to ask questions
[20:10] about and throw it onto your machine.
[20:12] So I copied over to my WSL machine and
then I ingested it with this command once
[20:16] complete and I ran private GPT. Again,
[20:18] here's all my documents and
I'm ready to ask it questions.
[20:21] So let's test this out. I'm going
to ask it what did I do in takayama?
[20:26] So I went to Japan in November of 2023.
Let's see if you can search my notes,
[20:31] figure out when that was and what I did.
[20:36] That's awesome. Oh my goodness.
[20:41] Let's see, what did I eat in Tokyo?
[20:45] How cool is that? Oh my gosh,
that's so fun. No, it's not perfect,
[20:49] but I can see the potential here.
That's insane. I love this so much.
[20:53] Private AI is the future and that's why
we're seeing VMware bring products like
[20:57] this to companies to run their own
private local AI and then make it pretty
[21:01] easy. If you actually did that private
GPT thing, that little side project,
[21:04] there's a lot to it. Lots of tools you
have to install, it's kind of a pain.
[21:07] But with VMware,
[21:08] they kind of cover everything like that
deep learning VM they offer as part of
[21:11] their solution. It's got all the
tools ready to go. Pre-baked again,
[21:15] you're like a surgeon just
walking in saying scalpel.
[21:17] You got all this stuff right there. So
if you want to bring AI to your company,
[21:20] check out VMware private AI link below
and thank you to VMware by Broadcom for
[21:24] sponsoring this video. You made it to
the end of the video time for a quiz.
[21:28] This quiz will test the knowledge you've
gained in this video and the first five
[21:32] people to get a hundred percent on this
quiz will get free coffee from Network
[21:36] Chuck Coffee. So here's how
you take the quiz right now.
[21:38] Check the description in your
video and click on this link.
[21:41] If you're not currently signed into the
academy, go ahead and get signed in.
[21:43] If you're not a member, go ahead
and click on sign off. It's free.
[21:47] Once you're signed in,
[21:48] it will take you to your dashboard showing
you all the stuff you have access to
[21:51] with your free academy account.
But to get right back to that quiz,
[21:54] go back to the YouTube video,
[21:55] click on that link once more and
it should take you right to it.
[21:58] Go ahead and click on start now and
start your quiz. Here's a little preview.
[22:03] That's it. The first five to get
a hundred percent free coffee.
[22:06] If you're one of the five,
[22:06] you'll know because you'll
receive an email with free coffee.
[22:09] You got to be quick, you got to be smart.
I'll see you guys in the next video.