How To Fine-Tune A Large Language Model (Step-By-Step)

AI is great at a lot of things. Sounding

human is not one of them.

>> Aa vista baby.

>> So when it comes to the promise of making our lives easier, specifically when it comes to writing things like blog posts and articles and scripts or social media posts or whatever, we still

need to spend a ton of time reviewing and editing the work before publishing.

But that can end right now. In this

video, I'm going to walk you through a step-by-step process on how to make LLMs sound more like you, Ron. Sorry, were

you talking to me?

>> Unless, of course, you aren't human. Are

you human, Ron? Anyway, this video is a complete guide to fine-tuning your large language models. I'll show you some use

language models. I'll show you some use cases specifically related to copywriting and my own needs, but the applications really are limitless. So,

without further ado, join me on this journey.

Before we get too deep, let me explain what fine-tuning is. So fine-tuning is basically teaching an AI to act a certain way as opposed to know certain

things. So imagine you hire a writer for

things. So imagine you hire a writer for your YouTube channel to help you write scripts. If you give them a Google Drive

scripts. If you give them a Google Drive full of research material, well, they'll know all of the facts that need to go into the project, but they still don't know how to write or talk like you. So

fine-tuning is the process of giving that writer repeated examples of exactly how you talk. and you give them so much of that that eventually they naturally start sounding like you.

>> That's not creepy at all.

>> You may have also heard of rag or retrieval augmented generation. It's

another way to give additional context and details to a model. However, the

difference between rag and fine-tuning is that rag is more like giving your writer a giant reference manual with details and facts that they can pull from, but it's not going to change the

way they actually respond stylistically.

they'll just now have the ability to know and retrieve that additional information. So when you fine-tune a

information. So when you fine-tune a model, you basically start with one of the big general models that are out there that's trained on a ton of information and then you give that model

specific examples of the sort of outputs that you want from it. That process is then repeated over and over and over again until it learns your tone, your

structure, your formatting, your jokes, your habits, and your preferences. So

the simplest comparison is basically rag is like giving AI access to your notebook so it has all the information that it needs. Fine-tuning is more like giving it acting lessons so that it

actually becomes more like you and starts to respond just like you. So if

you need a model to know and understand certain details, you could feed those details to the model through rag. That's

basically what you're doing when you upload PDFs or text files or things like that inside of chat GPT. If you want the model to talk like you, Rag's not going to quite cut it. You need to actually

fine-tune the model to achieve this.

Here's a model inside of a platform called Nebus that I've already fine-tuned. You can see this one's

fine-tuned. You can see this one's called MW YouTube, and it's built on top of Llama 3.37B Instruct. With this particular model, I

Instruct. With this particular model, I trained it on all of my YouTube transcripts. Like probably a hundred

transcripts. Like probably a hundred hours worth of training data transcripts from my videos. The idea being that I can tell it to go write a script on any

topic I want in the style of me and it will write a script that sounds the way I would talk on a video. If I go into the playground here, this is my fine-tuned model and I can give it a system prompt and I can chat with it

just like I would chat GPT. And I am going to get to a step-by-step breakdown in just a minute. I just want to finish showing off this example that I already did and then we'll do one from scratch.

In my system prompt, I'm going to go ahead and say, "You are Matt Wolf. Use

correct punctuation and markdown." And I can give it a prompt like create a detailed outline with 6 to 8 H2 sections for a 10-minute YouTube video on Nvidia's dominance and AI. Label with #

headers and three to five bullets per section. I just want to give it some

section. I just want to give it some extra details cuz like with any large language model, the more context you can get it, the better the output you're going to get. Now, if I submit this, theoretically, it's going to write a

script for me that sounds similar to how I would write. And that's exactly what it did here. But I can also compare it to what it would have looked like if I didn't use a fine-tuned model. So, if I

go to compare here and then I switch this second model on the right to let's go llama 3.370B instruct, that is the same model that I previously fine-tuned

here. Let's go ahead and clear our chat

here. Let's go ahead and clear our chat on the left and I'll give it a prompt.

Write an outro and closing to a video that wraps up why Nvidia is so dominant in AI. So, let's go ahead and give it

in AI. So, let's go ahead and give it that and let it write an outro for us.

And we can see sidebyside comparisons of how it would write that outro. how the

unfineted model did a little bit better with formatting, but that actually makes sense because I gave it just a ton of transcripts from YouTube videos. And if

you've ever looked at the transcripts from YouTube videos, there's usually not much formatting or punctuation. So, it

kind of overfit for that. But if we look at the normal llama response as we conclude our explanation of Nvidia's dominance in the AI landscape, it's clear that their success can be attributed to a combination of strategic

innovation, forward thinking, investment, and relentless pursuit of technological advancement. And then the

technological advancement. And then the version that's trained to sound kind of like me. So there you have it. That's

like me. So there you have it. That's

why Nvidia is so dominant in AI right now. They've been preparing this moment

now. They've been preparing this moment for over a decade. They're the leader in the hardware that's required to train AI models. They're the leader in the

models. They're the leader in the hardware that's required to run AI inference. and they're even building

inference. and they're even building their own AI models. Now, I'm not going to read the whole thing, but it's even trained on some of my old calls to action that I used to put in my videos.

If you've watched a lot of my videos, you know that this reads like me.

Hopefully, you found this video helpful.

Hopefully, you feel more looped in on the whole Nvidia ecosystem and why everybody's making such a big deal about Nvidia. We could even see here it went

Nvidia. We could even see here it went on to say, "If you like stuff like this and you want to stay looped and in the AI world and the latest AI tools, get the TLDDR of everything that's going on in the world of AI, check out

futuretools.io. Thank you so much for

futuretools.io. Thank you so much for tuning in. I really, really appreciate

tuning in. I really, really appreciate you. And thanks again to Wiretock for

you. And thanks again to Wiretock for sponsoring this video. I'll see you guys in the next video. Bye-bye." Now, it's funny because Wiretock hasn't sponsored the channel in like a couple years now, but that's in the training data. So, it

wrote an output that sounds like what I would have written. Now, granted, the formatting sucks, but that's my fault on the way I trained in the data. I didn't

clean up the data. I just gave it sort of unforatted transcripts, so it gives me back unforatted transcripts. Garbage

in, garbage out. So, real quickly, here's how I train that one, and then we'll start a new training from scratch.

I found this random website called downloadyoutubet transcripts.com. It

downloadyoutubet transcripts.com. It

looks pretty quickly made and slapped together, but for seven bucks, I was able to download all of the transcripts from my YouTube channel in one click. It

exported all of those transcripts as just one giant text file. You can also export them as individual text files, but for our use case, I just wanted it all in one huge massive text file. I

then took that giant text file that it generated and I uploaded it straight into ChatGpt and I gave it this prompt.

So, I'm not going to read the whole thing, but feel free to pause to get the exact prompt. But the idea was this

exact prompt. But the idea was this giant transcript document was not properly formatted to be used as training data. So, it needs to be a JSON

training data. So, it needs to be a JSON L file and it needs to be formatted in a certain way to show like a user input and then what the expected output is so the model can train on this input

deserves this output. And so, in order to do that, I had chatgpt do it for me.

I asked it to format the entire document in the proper JSON L format required by Nebius. It should give me two files at

Nebius. It should give me two files at the end. One with the training data set

the end. One with the training data set with 10% held back and the validation set with with the additional 10% of prompts and transcripts. I'll explain

that when we do our own version here in a minute. But the long and short of it

a minute. But the long and short of it was I gave it this entire transcript text file, told it to convert it to a JSON L file and format it in a way that Nebius would like. It took 14 1/2

minutes to do that for me, but as you can see, it gave me two files to download. The training JSON L file and

download. The training JSON L file and the validation JSON L file and then went to Nebus fine-tuning, create a job, uploaded my training data set here and

my validation data set here and ran the training model. I can also download the

training model. I can also download the direct weights if I wanted here. So if I downloaded the files in our epoch 11 here, this is going to be the most advanced version, the most trained up

version of the model. So I can download the files that I need and I can use them offline if I want in a tool like LM Studio or O Lama or something like that.

All right, so I show you what it was capable of and then I probably confused you by showing you what I just did to get the YouTube one. So now let me try to unconfuse you by doing it step by

step with you.

>> Huh? In this next example, I want to train it up on all of my tweets that I've ever written. I want to be able to ask it to write a tweet in my style on any topic I want and have it write a

tweet that reads just like all of the other tweets I've ever made. Before we

get back to the video, I want to show you how to actually make money on YouTube. I run my YouTube channel sort

YouTube. I run my YouTube channel sort of like a business because, well, it is my full-time job. And if I learned anything from Econ 101, it's that, well, businesses need revenue. I manage all of my brand partnerships, events,

newsletter posts. Basically, the engine

newsletter posts. Basically, the engine that powers this YouTube car all in notion. Now, I need to blur a lot of

notion. Now, I need to blur a lot of stuff on the screen because I get access to quite a bit of confidential information that brands have trusted me with. So, yeah, but I just wanted to

with. So, yeah, but I just wanted to show you that I am using Notion and Notion just released their own in-platform AI agent that's going to make running any project or business so much easier. Instead of just chatting or

much easier. Instead of just chatting or suggesting ideas like a lot of other AI tools, Notion's agent can actually complete multi-step tasks end to end.

So, I can say something like, "Summarize my past three meeting notes into a checklist and send me a reminder on Monday." And it'll create the whole

Monday." And it'll create the whole operation inside Notion without me having to learn how to set up an automation or create a new board. Now,

Notion is not only so much easier to set up your whole project in, but also easier to manage your ongoing tasks and priorities. And since this is all

priorities. And since this is all powered by AI, Notion's agent can learn your style, remember your preferences, and even be customized with its own name and personality. I think I'll call mine

and personality. I think I'll call mine Steve. So, whatever you're working on,

Steve. So, whatever you're working on, from content creation to business management or somewhere in between, Notion can help you set it up and keep it running smoothly. Try it out and let Notion Agent do your work for you at the

link in the description. And thank you so much to Notion for sponsoring this portion of today's video.

So step one in order to do that is we need to download all of our Twitter or X data. So if I'm logged into my X account

data. So if I'm logged into my X account here and I go to more and I click on settings and privacy under your account there's an option for download an archive of your data. So I'm going to select that. It's going to ask me for my

select that. It's going to ask me for my password and there's a button here to download the archive. Now for some weird reason, I don't know why X does this. It

makes you wait 24 hours before you actually get the download. So, if you press the download button now, 24 hours from now, there will be an email in your inbox saying your download's ready. It's

stupid. I don't know why they do it that way, but you can't just get your data immediately. It needs 24 hours to

immediately. It needs 24 hours to process. Luckily, I clicked this button

process. Luckily, I clicked this button 24 hours ago, and I can click into download archive. And we can see that it

download archive. And we can see that it was generated, and I can now download my archive here. It's large. It's 13

archive here. It's large. It's 13

gigabytes, but we're just going to pull out the tweet data from it. Here's the

zip file that I just downloaded. I'm

just going to go ahead and unzip it real quick. Once it's unzipped, we'll have

quick. Once it's unzipped, we'll have two folders. If I go into the data

two folders. If I go into the data folder here, there is a file called tweets.js.

tweets.js.

And as we can see, it's basically the second largest file in here. If I open this with, let's open it in a text editor, we can actually see this is all of my tweets. This is actually showing a

retweet, my AI news roundup. Now, it

looks like the data that it pulled in is just pulling in the first, I don't know, 140 to 280 characters. It's not pulling in the full long tweets if you did a

long tweet, which is unfortunate, but hopefully the data is enough to use to train close enough.

So, I'm going to grab this tweets.js js file here. And I'm just going to move it

file here. And I'm just going to move it to this folder so it's easy for me to find. We'll go ahead and create a brand

find. We'll go ahead and create a brand new chat inside of chatgpt. And here's

the prompt I'm going to give it.

Attached is all my tweets for my X account in a JS file. Create a script that converts this into the proper JSON L formatting for fine-tuning a model. It

should look at the tweet, think of a prompt that would have generated that tweet. For example, create a tweet about

tweet. For example, create a tweet about the Perplexity Comet browser in the style of Matt Wolf. And then it should format the entire document into the proper JSON L format required by Nebus.

It should give me two files at the end.

One with the training data set JSON L with 10% held back and the validation set with the additional 10% of prompts.

And actually I need to change this to tweets. So this is the prompt I'm giving

tweets. So this is the prompt I'm giving it along with the tweet.js file that we just looked at. We'll

submit this and it might take 15 minutes to run again, but it's going to go and make those files and prepare them for uploading into Nebius here in a second.

If you're wondering why I split it off into two files where the training data set is 90% and then we have a validation data set of 10%, well basically the

model is going to train on the training data set, the 90% that we gave it and then that final 10% is sort of like for the AI model to doublech checkck its

work. So basically, if the model was to

work. So basically, if the model was to give it an input that our validation data has a similar output for, how close did the model get to what our validation

model looks like? I don't know if I'm being clear here, but it's basically training on the 90% and then the 10% is so it can double check its work and see if it gets a close response to what's in

the validation data set. Hopefully that

computes. And this time, for whatever reason, it only took a minute and a half. Woohoo. But we can see it gave us

half. Woohoo. But we can see it gave us a couple files here. The training JSONL file and the validation JSON L file. So

let's go ahead and download both of these. We can actually see what chatgpt

these. We can actually see what chatgpt just did for us. It reads the tweets.js export, parses the tweets, filters out retweets and tiny junk tweets, generates

a synthetic prompt for each tweet in your style, splits it into 80% train, 10% validation, 10% held out. It sort of misunderstood what I was trying to do there. I wanted a 9010, not an 801010,

there. I wanted a 9010, not an 801010, but this should still work just fine. I

doubt that'll have much of an impact.

And then it wrote the instruction style Nebius JSON L. So, if we take a look at the files it just generated, let's go ahead and open this just with a text editor real quick. And we can see here's the cleaned up file. If we look at our

JSON L file, there's prompts and there's completions that it created for us around every single tweet. And it's all properly formatted.

So now if I head over to this Nebius platform here, you can find it at tokenfactory.nebius.com.

tokenfactory.nebius.com.

And then if we click into fine-tuning here, this is where we can fine-tune our models. Now, this isn't free to do. It

models. Now, this isn't free to do. It

does cost some money for inference to use Nebus to do the fine-tuning. The

pricing depends a lot on the model you're fine-tuning and the amount of data that you're feeding it. But this is not sponsored by Nebus. It is literally just the easiest way I found to do this

process. So, inside the fine-tuning

process. So, inside the fine-tuning page, I'm going to click create job.

Under training data set, we'll upload the MW tweets train JS JSON L file. For

our validation data set, we'll upload our tweets-val.

And now we can click continue. Now, for

training type, I'm going to do Laura fine-tuning. It is quicker and cheaper

fine-tuning. It is quicker and cheaper to run. For our model, we have a few

to run. For our model, we have a few options to select from, but in order to be able to just use the model directly inside of Nebius here, you want to click one of these models that has one-click

deployment. Otherwise, you're going to

deployment. Otherwise, you're going to need to download your weights and like run it locally or run it in some other cloud service, and I just want to keep it all in one platform to keep it easy.

The first example I showed you, I used Llama 3.37DB instruct. For this particular example,

instruct. For this particular example, because it's writing tweets, like smaller text segments instead of long scripts, I'm actually going to use the 8B instruct, the smaller model. If

you're trying to decide which model to use as your base model to fine-tune on top of, here's something that could help. Here's an example of an 8B model,

help. Here's an example of an 8B model, a 32B model, and a 70B model. This is

the amount of parameters inside of the data set. The larger the model, the more

data set. The larger the model, the more expensive and the longer it's going to take to fine-tune it. The smaller the model, the faster and the cheaper it's going to be to fine-tune, but also you

might lose a little bit in accuracy and it won't be very good at long content.

So, Llama 38B Instruct, the one we're using for this demo, is great for things like tweets, hooks, and intros. The

style accuracy will be pretty dang good, but it won't be long form coherent. It's

going to struggle with really long prompts. is going to struggle with

prompts. is going to struggle with really long outputs. But as we can see, cost to train and deployment costs are low. And then if we jump to the 70B

low. And then if we jump to the 70B model, I'm just going to skip over Quinn 32B cuz that's not one of our models that is instantly deployable. You can

see this is better for documentary style storytelling. So you're going to get

storytelling. So you're going to get more style accuracy. It's going to get more closely trained on your style than had you used a small model. And it's

going to have that long form coherence.

though you can give it longer prompts on input and it's going to be able to output longer responses. However, more

expensive to train, more expensive to deploy, and probably overkill for most use cases unless you're doing YouTube scripts or very long blog posts. All

that being said, let's jump back to Nebius here. And again, we're going to

Nebius here. And again, we're going to stick with our Llama 3.1 8 billion parameter model here. The model you choose will affect the pricing. So, this

one is only 40 cents per million tokens.

If I was to switch this to 70B, you can see now it's $2.80 per million tokens.

So, we want cheap and fast. So, for

training type, we're using Laura finetuning. For batch size, I'm just

finetuning. For batch size, I'm just going to leave it at eight. For learning

rate multiplier, I'm going to put 0.001.

Number of epochs is 11. Warm-up ratio

003. Weight decay. 01. Max gradient norm one. And enable packing on. You don't

one. And enable packing on. You don't

really need to worry too much about what these do. The number of epochs is how

these do. The number of epochs is how many times it's going to sort of pass through the training data. So the bigger amount of epochs probably the better the output is going to be. But there is a

point of diminishing returns where continuing to train it more and more and more just further overfits it to a point where you're not going to get good outputs anymore. In my testing, setting

outputs anymore. In my testing, setting it at around 11 seems to work fine. The

rest of these numbers I've saw on a blog post somewhere that that was what was recommended. I've stuck with those.

recommended. I've stuck with those.

They've worked fine. For Laura rank, I'm setting it to 16. Laura alpha 32. Laura

dropout.05. And then for the suffix for output model name, I'm setting it to Matt's tweets so I can find it easier.

I'm going to click continue here. It's

going to ask for some weights and biases API keys. I'm not using them. They're

API keys. I'm not using them. They're

not necessary. We'll click create job.

And now we can see the status is it is running this job here. Now, this process could take anywhere from 10 minutes to 4 hours, depending on which model you're fine-tuning on top of, how big your

training data is, and various other factors. The amount of epochs you set,

factors. The amount of epochs you set, things like that will change the amount of time. I've had a model fine-tune take

of time. I've had a model fine-tune take 45 minutes. I've also had a model

45 minutes. I've also had a model fine-tune take 5 minutes. Again, a lot of factors could affect the timing.

Okay, and that model is done running. We

started the model training at 5:19 p.m.

and it finished at 5:26. So, it took about 7 minutes to train that model. If

I click on deploy and download checkpoints, I can download the strongest weight here and use it wherever I want. And we know the training did its job when the training

loss is decreasing with each new epoch here, which we can see it did. And the

validation loss is increasing with each new epoch. So perfect. As far as cost

new epoch. So perfect. As far as cost goes, for me to fine-tune that model at 40 cents per million tokens, it cost me $2.56.

I have a lot of tweets. It fed it 6,43 tokens. For comparison though, when I

tokens. For comparison though, when I trained my YouTube videos on Llama 70DB, it cost me 75 bucks. What? Because I was

using 70B, it cost me $2.80 80 cents per million tokens and I fed it almost 27 million tokens. So yeah, it was a little

million tokens. So yeah, it was a little bit more expensive to fine-tune it on my YouTube videos, but again, if you want a model that sounds just like you, this is a one-time cost.

Now, let's go test our Twitter model.

So, I'm going to jump back to the fine-tuning page where we just fine-tuned this thing here. Click on

deploy and download checkpoints. And

then under epoch 11 here, we're going to deploy this model. This is going to be the best trained model for Allora adapter. I'm going to call this MW

adapter. I'm going to call this MW tweets. And I'm just going to say

tweets. And I'm just going to say trained on Matt Wolf's tweets. Click

start deployment. And it's going to fire up an inference server for this model.

Deployment started. Let's go to custom model. And we can see under my model

model. And we can see under my model endpoints here, I've got my original Llama 3.370B model and my new model here, which is 3.18B. And we can see

it's running the MW Tweets Laura on top of it. Now, it's still deploying, but we

of it. Now, it's still deploying, but we can see it's going to cost basically nothing to use it. Once it's deployed, I can click on go to playground. All

right. So once I'm in the playground here and I have my model loaded in, I can ask it to write a tweet in the style of Matt Wolf about how AI and VR are about to intersect in a big way. The

tweet should be at least 240 characters.

And this was the tweet it wrote for me.

AI and VR are about to intersect in a big way. I just got back from CES and

big way. I just got back from CES and there was a ton of head-tracking VR devices on the show floor. Meta just

open sourced their fair share of VR head-tracking tech. We're seeing a rush

head-tracking tech. We're seeing a rush of new VR headsets coming in the coming months. So, I mean, it wrote just like

months. So, I mean, it wrote just like me and even got from the training data that I've been to CES. I think it got that from the training data at least.

Now, let's compare that to if I just used a regular model. I can click on this compare button here and then I can change this model up here to a different

model. Unfortunately, the Metal Lama

model. Unfortunately, the Metal Lama 3.18B instruct model that I've been testing with, it's not working in Nebius. So, if

I use this model, I'd give it the same exact prompt. We can see it says failed

exact prompt. We can see it says failed to get model response. So, something is wrong with Nebius's connection to Llama 3.18B. But if I switch it over to let's

3.18B. But if I switch it over to let's go 3.37DB.

So, it's a larger model, bigger, more parameters in the training set, but not totally apples to apples, but I still think my version is going to be better.

So, if I give it this same prompt here, we can see this model is working. And

here's the tweet that just a normal non-fine-tuned model wrote. Wakeup call.

AI and VR are on a collision course and it's about to change everything. Imagine

neural networks generating photorealistic worlds in real time, adaptive difficulty that adjust to your skills, and avatars that learn your behavior. The future of immersive tech

behavior. The future of immersive tech is arriving fast. # AI #VR. I never use hashtags on Twitter, like ever. So, none

of my tweets on this fine-tuned model are ever going to need to have hashtags in them. Yet, for whatever reason, AI

in them. Yet, for whatever reason, AI likes to throw hashtags in anything it thinks is a tweet. This also doesn't read like me and is just not looking like a tweet I would have wrote. So,

let's go ahead and clear both chats again. Write a tweet in the style of

again. Write a tweet in the style of Matt Wolf about why tacos are the best food ever. It should be at least 240

food ever. It should be at least 240 characters. Let's give this to both

characters. Let's give this to both models. My fine-tuned model and the

models. My fine-tuned model and the Llama 70DB model. I just wrote a simple tweet. Why are tacos the best food ever?

tweet. Why are tacos the best food ever?

I mean, that's probably something I would write. On the other hand, 70B

would write. On the other hand, 70B instruct, tacos, folks are the apotheiois of culinary perfection, a harmonious union of textures, flavors, and temperatures all converging in a

delicate crispy shell. The crunch of fresh lettuce, the tang of salsa, the richness of carneasada. It's a

gastronomic symphony. # tacos for life.

I mean, honestly, one of these tweets looks more like a tweet that I would have written. Now, there is one quick

have written. Now, there is one quick sort of gotcha that I skipped over cuz I actually did it while I wasn't recording. But I was asking it to write

recording. But I was asking it to write tweets for me. And every single tweet it wrote actually put an at reply in it.

So, every single one started with like Rowan Chung, Matthew Berman, Robert Scoble. They all started with like at

Scoble. They all started with like at tagging somebody. Obviously, I didn't

tagging somebody. Obviously, I didn't want every tweet it ever writes for me to tag other people. And what happened was when I asked ChatGpt to rewrite all

my tweets using proper JSON L that can be accepted by Nebius. Well, it scraped all of my tweets, but it also scraped all of my replies to other people's tweets. And I have way more replies to

tweets. And I have way more replies to other people's tweets than I have my own tweets. So, it definitely overfit on me

tweets. So, it definitely overfit on me replying to other people on Twitter. So,

every single tweet it generated sort of tagged somebody in it. So, what I did was I went to chat GPT, ran that same prompt again where I asked it to reform

it to Jason L for me, but this time I said remove any replies and only add tweets that I wrote on my main timeline to the data set. It cleaned it up and

now I have a data set that I fine-tuned that doesn't try to at reply everybody all the time.

And that's how you do it. That's how you fine-tune a model with the easiest method I found. Now, people may claim that methods like rag will get it to talk more like you. But that's often not the case. You can kind of use rag to

the case. You can kind of use rag to give it some examples and say kind of write it like this. But then the AI models are still going to sort of write it how they want to write it. But if you write blog posts or make YouTube videos

or post on social media often or really need to do any form of marketing where the outputs need to know your voice or your brand's writing style, fine-tuning might be a good option for you. Now,

obviously, it's a bit more technical than just firing up something like chat GPT. But if you want to know how like

GPT. But if you want to know how like power users of AI are using some of these models to make content that's practically indistinguishable from what they'd make without AI, well that's what

fine-tuning does for them. Eventually,

I'm sure ChatGpt and Claude and Gemini and all those platforms are going to have fine-tuning just sort of built in and it's going to make it so much easier to make these models sound like you. But

for right now in 2025, this is the simplest process I've come across. If an

even easier method comes along and makes it super simple to make AI sound like you, I'll probably make another video and update how to do it with the even easier way. But for now, this is what

easier way. But for now, this is what we've got. Hopefully, you found this

we've got. Hopefully, you found this helpful and understand a little bit more about fine-tuning and how to dial in the voice of your AI model. I've made it my full-time job to keep up with the latest AI news and test all of the latest

tools. So, if you want to stay looped in

tools. So, if you want to stay looped in on the latest advancements, as well as get deep dive tutorials on how to actually use the tech, make sure you like this video and subscribe to this channel, and I'll make sure more videos like this keep showing up in your

YouTube feed. So, thank you so much for

YouTube feed. So, thank you so much for nerding out with me on this one. I

really appreciate you, and hopefully I'll see you in the next one. Bye-bye.

Thank you so much for nerding out with me today. If you like videos like this,

me today. If you like videos like this, make sure to give it a thumbs up and subscribe to this channel. I'll make

sure more videos like this show up in your YouTube feed. And if you haven't already, check out futuretools.io. io

where I share all the coolest AI tools and all the latest AI news. And there's

an awesome free newsletter. Thanks

again. Really appreciate you.