Train a Custom GPT LLM Using Your Own Data From Scratch

The model will learn to reply in the same way you would. After preparing your data, you'd need to run commands to install Rust and OpenCL libraries for GPU support, then start the training process.

[SaturnKK]

Keyvan here, thanks for your great video ❤

[avi]

There's going to come a day when you can train a GPT-5 level model on an old computer and that's gonna be hilarious and quaint like running 20 different game emulators on a raspberry pi or something.

[googleyoutubechannel]

This would have been a lot more interesting if you'd actually done the work of even a single full example like you were describing... running on all your emails for instance.

[punchnergy]

Would've been nice if you would show how to make it into a chatbot :)

[MrStevemur]

I'm guessing it wouldn't be any smarter than the predictive text feature on a phone, since it's only predicting which letter is most likely to come next. If you can understand the code though, it could be interesting as an example of how these work.

[videosmydad]

Thank you Stephen for answering my last question. I have another one!

are you supposed to delimit in the training set between the different inputs?
my set looks like:

user_input=<hello, how are you?> agent_output=<i am fine>
user_input=<how is the weather today?> agent_output=<i think its sunny>

.
.
.

is the GPT reading my entire file as one input, or do I need to separate each conversation, or does it matter?

this way, when i use the GPT, i want the code to be:

prompt = "user_input=<" + input + "> agent_output=<"

and inference should hopefully finish the agent_output....

thanks

[bruninhohenrri]

Hey ! I finally had time to test it. Now that i have the model, how could it inference it ? Thanks for the video !

[StephenBlum]

Command: cargo run --features gpu --release

[videosmydad]

I have just started the training on some data.

How do I test it?

Where do I give it a sentence and have it finish it?

I think its:
let inference = gpt.infer(
&mut rng,
&tokenizer.tokenize("\n"),
100,
inference_temperature,
|_ch| {},
)?;
replace the '\n' with my prompt?

thanks

[TimJSwan]

ironically I was hoping to use the apple silicon for its neural engine yet this project uses amd and intel

[JehovahsaysNetworth]

I’m updating my ai for PHP html js and css and it can build templates

[utpalprajapati]

is there any such program for python/javascript devs?

[shaileshrana]

Hey Stephen. Great explanation.
I am trying to train a model on Jira tickets. Can you suggest the way I can format the data in the dataset file.
I want to give the description of the ticket. The comments with the commenter name. The state changes and the values of other parameters and their changes like assignee name.

This is the kind of thing I have in mind:
NUMBER: BACK-356 /n
TITLE: Invoice dump job failure /n
DESCRIPTION: The job for ingesting invoices from the Production tables has failed on June 26th, 2024. We need yo resolve this because the financial reporting is due at the end of the month. /n
ASSIGNEE: Ramesh Vesvaraya /n
COMMENT: /n
WRITER: Ram Gupta /n
BODY: @Saurabh Sharma can you look into this.