Fine-tuning ChatGPT with OpenAI Tutorial - [Customize a model for your application in 12 Minutes]

แชร์
ฝัง
  • เผยแพร่เมื่อ 6 ม.ค. 2025

ความคิดเห็น • 93

  • @Corbin_Brown
    @Corbin_Brown  9 หลายเดือนก่อน +3

    Navigate to key moments👇
    made via tubestamp.com
    0:03 - Understanding the concept of fine-tuning models
    1:44 - Importance of providing example inputs and outputs for fine-tuning
    4:09 - Importance of having 10 different data points for fine-tuning
    6:30 - Minimum of 10 example data points required for training
    9:46 - Training cost estimation and model success
    11:32 - Leveraging fine-tuned models in OpenAI playground

  • @strategy419
    @strategy419 9 หลายเดือนก่อน +6

    explain when you mentioned at the end of the video to “try jason or jvsc “ before finetuning if prompting didnt work. can you explain how to try json and java scripts what did you mean

    • @Corbin_Brown
      @Corbin_Brown  9 หลายเดือนก่อน +5

      Try using code to refine the outputs before using a fine-tuning model. For example, if in your outputs you are continually getting "", then write lines of code to remove "" from the output rather than updating the underlying prompt or model.

  • @Mnkeys
    @Mnkeys 8 หลายเดือนก่อน +7

    You're a LEGEND. Can't tell you how helpful this was

  • @Wahtel
    @Wahtel 10 หลายเดือนก่อน +3

    Awesome video!
    I would like to see more content of how you can improve the model and make it even more powerful for clients))
    It was awesome, if you could use then fine tuned model via another interfaces such as Zapier!

  • @IdPreferNot1
    @IdPreferNot1 10 หลายเดือนก่อน +2

    Nice to see some more technical vids, thx.

  • @vidithbalasa1237
    @vidithbalasa1237 10 หลายเดือนก่อน +5

    I get fine tuning a smaller model to be able to complete a task for cheaper but I feel like you’d need a really niche task to wanna fine tune chatgpt

    • @vidithbalasa1237
      @vidithbalasa1237 10 หลายเดือนก่อน

      I’m not tuned in though I’m sure people have lots of use cases

    • @Mnkeys
      @Mnkeys 8 หลายเดือนก่อน +5

      It's less about pricing and more about controlling the output. If you're trying to make a product to sell, you want some aspect of control over the output. Do you want OpenAi linking to competitors? Do you want it to get confused by bad information online? Fine tuning, in my mind, can often be used to get ahead of those issues and almost set "baselines"

    • @PerpetuallyTiredMillennial
      @PerpetuallyTiredMillennial หลายเดือนก่อน

      I can speak to a use-case for it after battling with developing an auto-grader for a bit, gpt base models just don't have the level of accuracy and consistency needed for certain tasks.

  • @Wladimirko
    @Wladimirko 10 หลายเดือนก่อน +1

    Very helpful and valuable content. thank you corbin!

    • @Corbin_Brown
      @Corbin_Brown  10 หลายเดือนก่อน +1

      Glad it was helpful!

  • @strategy419
    @strategy419 9 หลายเดือนก่อน +2

    more of fine tuning cideo like this please

  • @elprox1290
    @elprox1290 5 หลายเดือนก่อน +1

    TYSM!!1 I could not find another vid that was actuallly updated! thx

  • @planet-imagine
    @planet-imagine 10 หลายเดือนก่อน +1

    nice. has there been a decrease in costs for using a fine tuned chatgpt model ? because it was unreasonably expensive a few months ago.

    • @Corbin_Brown
      @Corbin_Brown  10 หลายเดือนก่อน +3

      The cost is sitting at around $3.00 per 1M tokens for input.
      That is why I would say try attempting to create an effective prompt with the base model or formatting the outputs before choosing to fine-tune a ChatGPT model like we did in this video.

  • @Alex-dk1um
    @Alex-dk1um 10 หลายเดือนก่อน +1

    Thank you for all the content so far. I work in a smaller company and want to be the go-to person for AI and specifically the section of AI you do your videos on. What would you suggest working on first? You should do some lessons even if those 'courses' are behind a pay wall, I want to learn everything.

    • @Corbin_Brown
      @Corbin_Brown  10 หลายเดือนก่อน

      My suggestion for anyone trying to leverage AI to its maximum capability is to get comfortable with automation platforms. Using platforms like Make or Zapier allows us to access external software and complete tasks automatically.
      Check out my playlist on my channel; I have over 100+ videos dedicated to this topic.

  • @andresgordillo4414
    @andresgordillo4414 8 หลายเดือนก่อน +2

    Hello, thank you for the video. I would be very grateful if you could answer this question! I have various data from a transport company about origin, destination, and description of the load, prices charged, and data that the company has collected. I want to create an OpenAI assistant that helps me calculate the cost of transport services. However, what I have seen is that finetuning is a good option to teach the model how to answer questions in a certain style and things like that. But not so much for giving it a broader dataset so that with this new information it can make calculations or have a broader context. Is this true? What should I do in my case where I want it to take this data and improve the calculation of transport rates?

    • @tismine
      @tismine 8 หลายเดือนก่อน

      Did you figure that out?

    • @andresgordillo4414
      @andresgordillo4414 8 หลายเดือนก่อน

      @@tismine What I'm trying to do is take the data, convert it in embedindding and pass it to file search as a csv. I still don't know if it will work, but it seems to me that it may work.

    • @DavidChrisof
      @DavidChrisof 7 หลายเดือนก่อน

      How are collecting the "various data from a transport company" like in excel or like a pdf file?

    • @clarissalima575
      @clarissalima575 2 หลายเดือนก่อน

      LLMs are language models and aren't good with calculations, unfortunately. What ChatGPT would be good for your case is finding the data that is on your documents (price, description, origin, destination), and then you could programmatically make the calculation based on the price that the LLM collected from the source.

  • @SpacingCake
    @SpacingCake 4 หลายเดือนก่อน +1

    What did you mean at the and 11:37 by using JSON or JavaScript formatting the output??

    • @JulioARivera
      @JulioARivera 3 หลายเดือนก่อน

      an example video of this would be great!

  • @sameer5663
    @sameer5663 24 วันที่ผ่านมา

    So my understanding is that fine tuning can be used to create chat bots aka customer service chat bots for companies. Is there a way you can them get the bot to be called on a website!? like an API call

  • @lstopak
    @lstopak 4 หลายเดือนก่อน

    is it possible to fix the output space to only return certain strings? i have tried implementing a RAG system, but it provides too many possible strings and the LLM does not perform well. so I would like to pre-bake this into the LLM if possible

  • @sunandansharma5643
    @sunandansharma5643 3 วันที่ผ่านมา

    just want to ask if it costs money to run these ? or does it have some free limit so people can test this ?

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w 5 หลายเดือนก่อน +1

    this is really well explained

  • @manwithnocode
    @manwithnocode 10 หลายเดือนก่อน

    Can i do it with like input size of 3000 tokens and output size of 1000 tokens or so?

  • @sameer5663
    @sameer5663 24 วันที่ผ่านมา

    im aware theres different methods:
    Chatbot Development Strategies
    Large Language Model Fine-Tuning
    When considering fine-tuning, you have several platforms to explore:
    OpenAI's GPT models
    Anthropic's Claude models
    Google's PaLM/Gemini models
    Open-source models like Llama
    is OPenAI the best?

  • @elias6068
    @elias6068 5 หลายเดือนก่อน +1

    I have a big database of categories and special code names. Is fine tuned right for me? I was thinking training chat bot to learn my database rather than giving it as data, I think it will be more costly.

    • @Corbin_Brown
      @Corbin_Brown  5 หลายเดือนก่อน

      It would be more costly; I would approach by attempting both options, see which gives the best results for the cost, and make a decision there. I lean towards untrained models.

    • @adammarek8822
      @adammarek8822 4 หลายเดือนก่อน

      I have a similar usecase and fine running provides low quality results. The trained model does not use the complete training data in answers plus halucinates a lot.

  • @paragbharadia2895
    @paragbharadia2895 9 หลายเดือนก่อน

    thankyou , got now little direction to fine tuning!

  • @albertomarengo3753
    @albertomarengo3753 4 หลายเดือนก่อน

    Thanks so much. When I fine-tune Gemini 1.5 flash I get a model with only 16k tokens context. Do you know if there is a way to retain the 1M window context? Why did they do it this way? I guess it’s a distilled fine-tuned model?

  • @zainulkhan8381
    @zainulkhan8381 9 หลายเดือนก่อน

    What changes will be in the the model link if suffix is null I have not defined any kind of suffix and when I hit the completion api I get 404

  • @aritra80
    @aritra80 7 หลายเดือนก่อน

    Thank you so much for this video! It was so helpful

  • @Ubuchu
    @Ubuchu 7 หลายเดือนก่อน

    I have a question. I followed all the steps and successfully fine-tuned my model. However, I don't see my fine-tuned model in the playground. The only options available are GPT-4, GPT-3.5 Turbo-1106, GPT-3.5 Turbo, and GPT-3.5 Turbo-16k. Why are other models, including my fine-tuned one, not appearing?

    • @Ubuchu
      @Ubuchu 7 หลายเดือนก่อน

      Found the answer, I just happened not to give access to those models in project settings under Limits in Project.

  • @viralreels1431
    @viralreels1431 4 หลายเดือนก่อน +1

    very helpful!!

  • @PankajMalhotra-s6l
    @PankajMalhotra-s6l 4 หลายเดือนก่อน

    Hello , is there any way so i can disable the moderation or profanity while fine tuning my model.

  • @EdouarddeGanay
    @EdouarddeGanay 4 หลายเดือนก่อน

    thanks, did you group somewhere interesting exemples for fine tuning ? I see why doing finue tuning, but I miss interesting business cases. Moreover, how do you add your face on your videos AND contouring it ?

  • @MuhammadHuzaifa-bg1tw
    @MuhammadHuzaifa-bg1tw 9 หลายเดือนก่อน

    why the finetuned model is not showing up in the GUI of assistant

  • @frenches1995
    @frenches1995 4 หลายเดือนก่อน +1

    it's nice only the upload file step of the documentation is where I'm swimming now. But I'm sure I will get this.
    To answer your question why I'm finetuning a model, it's because the standart model 4o-mini isn't strong enough to seperate languages reliably from one another and I'm hoping I can overcome that problem for a multilanguage podcast script generater.

  • @faffie1978
    @faffie1978 4 หลายเดือนก่อน

    Weird, I don’t have the option fine tuning in the left menu (plus subscription)

  • @tke-nationupsilonpi9544
    @tke-nationupsilonpi9544 5 หลายเดือนก่อน

    How do you fine tune it to write a book in a certain style for long content ? Thx

    • @Corbin_Brown
      @Corbin_Brown  5 หลายเดือนก่อน

      Your best approach would be developing a function that handles this in VSC or, alternatively, using automation software like shown here: th-cam.com/video/8zO0kJXmSG0/w-d-xo.html

  • @axelmontois3676
    @axelmontois3676 8 หลายเดือนก่อน

    Amazing video. There is jsut something that I don't understand. What to put in content in the fine-tuning file.

  • @pblcrmn
    @pblcrmn 4 หลายเดือนก่อน

    You're the man!

  • @huseyinkaragulle5953
    @huseyinkaragulle5953 5 หลายเดือนก่อน +1

    very helpful. thanks

  • @AlexandraSchoenberg
    @AlexandraSchoenberg 9 หลายเดือนก่อน +1

    Hi Corbin!! Your videos are so helpful. I would love a tutorial on integrating these fine-tuned OpenAI models easily into an Action in a custom GPT. I have been stuggling with getting the ChatGPT interface to always send inputs (in JSON format) to my specific fine-tuned model and output the results (also should be in JSON format). The model, which is actually a GPT-4 fine-tune, works seamlessly in the Playground though. Just wondering if you've tried this or plan to.

    • @Corbin_Brown
      @Corbin_Brown  9 หลายเดือนก่อน

      Thanks for the suggestion. I will look into adding this to my content agenda!

  • @zharasbekshyrakbay9457
    @zharasbekshyrakbay9457 4 หลายเดือนก่อน +1

    thanks👍

  • @alejandrovasquez8942
    @alejandrovasquez8942 9 หลายเดือนก่อน

    Hi, I think your video is great, but I have a question. I have already created assistants using OpenAI's assistant tools, but how do I apply this fine-tuning to an assistant that I've previously created? How would it be done in that case? Note, I'm talking about the assistants, not the agents, but the assistants that appear in OpenAI's admin panel.

    • @Corbin_Brown
      @Corbin_Brown  9 หลายเดือนก่อน

      When creating an assistant within the OpenAI dashboard, we do not yet have the capability to use our fine-tuned model as the base model.
      Fine-tuned models are used more in the context of calling the new endpoint to achieve better outputs within our software.

  • @keithkeith2106
    @keithkeith2106 4 หลายเดือนก่อน

    Awesome Vid!!! How do I keep my data file safe and secure when training a model.

  • @ChahakMentor
    @ChahakMentor 10 หลายเดือนก่อน

    Nice...

  • @ozbekadigya
    @ozbekadigya 7 หลายเดือนก่อน

    Hi.. is there a way to fine tune gpt4?

  • @rtkkjson
    @rtkkjson 18 วันที่ผ่านมา

    How to fine tune using long form contents?

  • @chrisder1814
    @chrisder1814 4 หลายเดือนก่อน

    hello could I make a small database with TH-cam URLs?

  • @douglas_dev1
    @douglas_dev1 9 หลายเดือนก่อน

    Great video! can you do one showing how to custom an assistant and calling it over api? ^^

  • @GTAVI_ARENA
    @GTAVI_ARENA 4 หลายเดือนก่อน

    Urgent Question!!! can i fine turn GPT-3.5 model locally on my pC?

    • @Corbin_Brown
      @Corbin_Brown  4 หลายเดือนก่อน +1

      Check out this video that shows all the AI models we can install locally on our machine: th-cam.com/video/zrNKfiCuqCs/w-d-xo.html

    • @GTAVI_ARENA
      @GTAVI_ARENA 4 หลายเดือนก่อน

      @@Corbin_Brown thank you, the video was so helpful … is there a tutorial yet on how to fine tune ollama 8b ?

  • @Dinheirosucessonline
    @Dinheirosucessonline 8 หลายเดือนก่อน +1

    Dude thanks for video, bit as soon you create a video where the final results is what we want see, please spend more time showing the results

  • @ese02
    @ese02 10 หลายเดือนก่อน

    Amazing tutorial. Thanks for sharing. PS: what kinda app/soft u use to produce ur videos (green screen ?)

    • @ese02
      @ese02 10 หลายเดือนก่อน

      I know u use OBS but how do u crop out ur background ?

    • @Corbin_Brown
      @Corbin_Brown  10 หลายเดือนก่อน

      I use an Elgato collapsible green screen and then set up the chroma key in the OBS settings!

    • @ese02
      @ese02 10 หลายเดือนก่อน

      Cheers Corbin. Keep Rocking \m/

  • @John-jt3dn
    @John-jt3dn 9 หลายเดือนก่อน +1

    great video Corbin.. thanks. Is 10 enough or the more the merrier?

    • @Corbin_Brown
      @Corbin_Brown  9 หลายเดือนก่อน +2

      In the context of training the model, the more data you provide, the more expensive it will be to train.
      Therefore, I would opt for high-quality 10 data points. If you notice more reliability but certain outputs still don't hit the mark, either add more data points or adjust the prompt.

    • @John-jt3dn
      @John-jt3dn 9 หลายเดือนก่อน

      Thank you very much. We want to be very accurate as much as we can regardeless of the cost. We just dont want to delude the dat with 1000s entries.@@Corbin_Brown

  • @PaulAcito-ce2ex
    @PaulAcito-ce2ex 4 หลายเดือนก่อน

    Corbin, Thanks for this and all your other great explainers! I fine tuned a model on 40 or so Rodney Dangerfield jokes, but don't know how to call it outside playground (it's pretty funny btw, but gets no respect). I am not a coder, any ideas?

  • @devbathani8020
    @devbathani8020 8 หลายเดือนก่อน

    how much did it costed you ?

  • @Sulayman.786
    @Sulayman.786 10 หลายเดือนก่อน +1

    Fine.

  • @thuantranuc5349
    @thuantranuc5349 3 หลายเดือนก่อน

    fine-tuning not support assistant ?

  • @SorinDecuseara
    @SorinDecuseara 4 หลายเดือนก่อน +1

    If you don't add System prompt (where you mention clearly Marv you are a funny/sarcastic chat bot) it seems that chat doesn't know to be funny/sarcastic if you ask the fine tunned model. The question is: if you add the System prompt to normal model it knows how to be funny without any training. so what the fine tune did in this case? (tested on gpt-4o-mini-2024-08-17)

    • @jackf6622
      @jackf6622 22 วันที่ผ่านมา

      I tried over 10 fine tuning jobs, using 70/ 30 split for validation. I had 0.8 loss on training and 0.2 on validation, pretty good score, i think. But it just doesn't work. We need proof that it works comparing a non tuned model to the tuned model with the same system prompt or no system prompt. Yet NOBODY has a video of showing this on TH-cam so I am wondering if this stuff actually works

  • @tuaitituaiti1565
    @tuaitituaiti1565 3 หลายเดือนก่อน

    💫🙏🎯👊🤙💪🗿🎬🔥🦅☯️ Thank You CB Great Value Add As Usual Sir

  • @tradingwithwill7214
    @tradingwithwill7214 3 หลายเดือนก่อน

    I've been thinking of creating a chatbot that talks like me so I want to upload all my chats, social media posts, likes etc. This is for my wife in case something happens to me, maybe I will upload all the things I do around the house and how to fix stuff etc lol. So fine tuning looks like the way to go. I don't like the system content variable they use it seems repetitive and usually my system prompt is fairly long so it'd be repeated on each line.

  • @jpsl5281
    @jpsl5281 8 หลายเดือนก่อน

    When Creating the dataset to train gpt-3.5-turbo
    For a conversational AI
    If I want to train the model to answer something specific to a range of similar questions that can occur during a conversation.
    *The conversation is a script which the AI follows*
    Should I include only the question and the response or should I include all the conversation up to where that specific question is asked ?

  • @lucasbergamo7607
    @lucasbergamo7607 4 หลายเดือนก่อน

    so... i think you will receive a lot of views if you find a way to delete a finetuned by API... because is very boring create a lot of finetuning and cant delete after if you not use anymore..

  • @rodrigovm
    @rodrigovm 2 หลายเดือนก่อน

    now your video is also 7 months old. I'll make a new one

    • @deroace
      @deroace หลายเดือนก่อน +1

      lied :(

    • @rodrigovm
      @rodrigovm หลายเดือนก่อน

      @@deroace wow never thought anyone would follow up on that

    • @deroace
      @deroace หลายเดือนก่อน +1

      @@rodrigovm then I gess dont write, when you dont mean it be a man

    • @okt4k
      @okt4k 18 วันที่ผ่านมา

      @@deroace still no video :(

  • @matthewv06
    @matthewv06 10 หลายเดือนก่อน

    who doesn't love AI?