DETAILED tutorial on how to fine-tune (train) GPT 3.5 Turbo with your own data in Bubble.io

Поділитися
Вставка
  • Опубліковано 15 січ 2025

КОМЕНТАРІ • 6

  • @bradensilcott3817
    @bradensilcott3817 Рік тому

    Thanks so much for this tutorial! It's going to go a long way for my client project and a personal project as well.

  • @thatQiao
    @thatQiao Рік тому +1

    50:00 It took 11 minutes to train the model.

  • @theaieyee
    @theaieyee 11 місяців тому

    Hey can you just help me understand that other third party services let's us train our model of chatgpt based on google docs, google sheets and we scraping. How can we train the model on these kind of data sources and also can we enable it to search on web? Please help me understand these thing. Thank you. Your videos are very helpful.

  • @parabunx
    @parabunx 11 місяців тому +1

    Does anyone knows If I add a file, does it delete the file before i send to Open IA or does it add to the previous data?
    If this i need to delete my previous file, does this mean that if I want to update my fine tune model, I have to recreate a complete file each time?
    Thank for this video its very clear and usefull :)

  • @parabunx
    @parabunx 11 місяців тому

    Hello i have an other probleme, does anyone knows ho te get the message result in backend it seems to not work....

  • @estudanterafael8600
    @estudanterafael8600 Рік тому +1

    Good morning, in my part start fine tuning job it is giving the following error when I make the api call
    There was an issue setting up your call.
    Raw response for the API
    Status code 400
    {
    "error": {
    "message": "File 'file-Ykn4lXIxulkGHukJ2bbEvBia' is in prompt-completion format. The model gpt-3.5-turbo-0613 requires data in the chat-completion format.",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_file_format"
    }
    }
    I don't know what it could be