@gingerbread_GB

This is a very important learning point. When I was watching your video, I agreed with you that it was not good the bot kept saying "I'm a very experienced person." But later on, when I dove into your json file, I realized that the dialogue in the file was bad. When I searched for "experienced" in the json, I got 61 hits, with the same "I'm not sure. I'm a very experienced person." over and over again.

So the model worked, your code worked, the bot learns exactly what you taught it in the dataset. If your dataset is bad, your bot will talk nonsense.

@bennievaneeden2720

Great video. Glad to see people actually debugging their code. It really helps to better grasp whats going on

@mmrr3610

Thank you for the tutorial you provided. It's very useful, but please try to speak slower because even AI can't understand what you're saying sometimes. Thank you.

@kaenovama

Ayy, this is what I've been looking for

@ilyas8523

great video, I was stuck on some steps until I found your video.

@ayeshashakeel

Thank you so much! This was really helpful!

@plashless3406

This is amazing. Really appreciate your efforts, brother.

@rishabhramola448

Really helpful!!! Deserve more views

@fp-mirzariyasatali1985

Its great to try multiple techniques

@elibrignac8050

Epic video, just one question: After saving the model, how can I load it and make inferences.

@georgekokkinakis7288

What if we don't add the <startofstring>< <endofstring>, <pad> and <bot> to the training data? I have a dataset where each sample is formated as [context] [user_question] [bot_answer] and each sample is separated from the next one by an empty line. I am using a pretrained model lighteternal/gpt2-finetuned-greek

@Websbird

Great help - Can you recommend any editor for windows just like yours? and is that possible for you to create a colab or kaggle for same project?

@rakesh2233

Great video, thanks. I am a beginner studying about these LLM's. I have a small doubt, 

I have seen people use different data formats to fine-tune different LLMs. For example, the following format can be used for Llama-2:
  {
    "instruction": "",
    "input": "",
    "output": ""
  }

and sometimes the format below is used for chatglm2-6b:
{
    "content": "",
    "summary": ""
  }

Is it related to what format was used for pre-training or actually both can be used for different llms, how do I organize my custom data if I want to fine-tune a llm?

@SabaMomeni-i1n

great video. just wondering why u used <bot? token between two parts? any reason?

@ucduyvo4552

Great Video, thanks

@amitvyas7905

Hi!
It was a good video.
I would like to know once the model is trained how can we check the accuracy? Can you generate a ROUGE score? That way we know how goo or bad the model is.

@shubhamkumar8093

Very Informative 😊

@jackeyhua

Hi there, very good video, really appreciate. Currently we are facing a problem that the input token does not generate any bot output, like <bot:>  <endofstring><pad><pad>. Can you help figure it out?

@ammar46

Nothing is generated for me. I used exact code as you used. Can you help understand why this is happening??

@lowolt_team

i have made my own:
<user> Text <End> Ai Text <End

is good?