How to tune LLMs in Generative AI Studio

แชร์
ฝัง
  • เผยแพร่เมื่อ 3 ธ.ค. 2024

ความคิดเห็น • 59

  • @googlecloudtech
    @googlecloudtech  ปีที่แล้ว +9

    🏗 What are you building with generative AI models?
    Let us know and subscribe for more AI tips and tricks → goo.gle/GoogleCloudTech

    • @John-jt3dn
      @John-jt3dn 7 หลายเดือนก่อน

      We are trying to build an intuitive AI copmanion with various conversatinal parameters on Vertex AI. We have tried to tune it in Google AI studio but it is buggy.(stuck in queue) As for the our fine tunin we have 4 parameters in percentages in 4 different columns, an input prompt and a desired response. How can we pass his structure in JSON format in the wayy ou describe it.

  • @jk.g
    @jk.g ปีที่แล้ว +10

    Thanks Nikita, this was really interesting and easy to understand as someone who doesn't do too much with AI/ML or data.

  • @GeorgeFoxRules
    @GeorgeFoxRules ปีที่แล้ว +15

    I’m taking all of my companies, documentation and experimenting with llama index and lang chain and open AIAPI. It would be cool to compare the same experiment with vertex AI and see what the results are with the same tuning dataset.

    • @floydshiffman
      @floydshiffman ปีที่แล้ว +3

      are u concerned with your IP or proprietary data being in the public domain

    • @craftedbysrs
      @craftedbysrs 6 หลายเดือนก่อน

      Have you found any notable result?

  • @richardglady3009
    @richardglady3009 ปีที่แล้ว +3

    Very nice video. You took complex issues and made them understandable to a layman (me). Thank you.

  • @devcybiko
    @devcybiko ปีที่แล้ว +8

    Thank you for an awesome presentation… However the background music was really distracted… Silence or something less noisy would be great

  • @lucas.souza2022
    @lucas.souza2022 ปีที่แล้ว +5

    I think APIs are one of the biggest ways to democratize technology.
    Thank you

  • @bolokada1
    @bolokada1 ปีที่แล้ว +1

    This video is worth seeing for my GEN_AI course. Thanks 👍

  • @j.heasly7365
    @j.heasly7365 2 หลายเดือนก่อน

    "GENERATIVE AI STUDIO > Language" doesn't seem to be an option anymore in the Vertex AI lefthand nav. There is a "VERTEX AI STUDIO > Tuning" option, which looks similar but seems to have been split into two steps since this video was made.

  • @YARIMASHAFIU
    @YARIMASHAFIU 9 หลายเดือนก่อน

    This is a very interesting presentation!

  • @jayanthacharya449
    @jayanthacharya449 6 หลายเดือนก่อน

    Great explainer video. It really dumbed down the process of training quite a bit. Would like to see similar videos on topics like RAG.

  • @mohamedkarim-p7j
    @mohamedkarim-p7j หลายเดือนก่อน +1

    Thank for sharing👍

  • @saikiranmadhavan9585
    @saikiranmadhavan9585 ปีที่แล้ว +2

    When i try to follow your instructions - i am not able to see the model run in the pipeline - i did everything as instructed and whenever i click on the start tuning button - nothing happens - somewhere i read the Tuning (Preview) happens in europe 4 region and i verified that the code generated looks good - any idea what am i missing ? Also in your screenshot it doesn't show the Model Evaluation section in the UI - may be it got added recently to this page

    • @mohaiminshoron4911
      @mohaiminshoron4911 ปีที่แล้ว

      were you able to solve the issue? i am having the same problem.
      And did you try the europe 4 region?

  • @NithinThomas
    @NithinThomas ปีที่แล้ว

    I’m redefining the meaning of Shelter with Gen AI!

  • @bisu4you
    @bisu4you 9 หลายเดือนก่อน

    his is a very interesting presentation!

  • @AGaneshmurthy
    @AGaneshmurthy ปีที่แล้ว

    Thanks giving these kind of cources

  • @call_of_duty1327
    @call_of_duty1327 ปีที่แล้ว +1

    Sentiment analysis can be done?

  • @NiccoloSala
    @NiccoloSala 6 หลายเดือนก่อน

    Where can I find the pricing plans to create a tuned model?

  • @rahulbats
    @rahulbats 8 หลายเดือนก่อน +1

    which base model is she finetuning ?

  • @joygha
    @joygha ปีที่แล้ว +1

    A very interesting video will ahve tod o some experimentation as I will try to create a model which is foccussed on solving learners queries

  • @KumR
    @KumR 10 หลายเดือนก่อน

    Great session. Just 1 QQ. So fine tuning is like transfer learning ?

    • @joshuatettey7771
      @joshuatettey7771 4 หลายเดือนก่อน

      Yes. Fine-tuning is a type of transfer learning.

  • @willian_z
    @willian_z ปีที่แล้ว

    2:53 summary paper link missing?

    • @willian_z
      @willian_z ปีที่แล้ว

      See the paper, thanks!

    • @econhelp583
      @econhelp583 ปีที่แล้ว

      @@willian_z I was thinking the same thing, and I still don’t see the link. Where is it exactly?

    • @willian_z
      @willian_z ปีที่แล้ว

      @@econhelp583 It’s the second Google link, “a guide to…”

  • @selvaips
    @selvaips ปีที่แล้ว

    Thank you for the insights. Really nice.
    I have built context prompts, did input few questions and sample responses but I do not have an option to tune this context prompts to fine tune further.
    Any suggestions on how i could fine tune my context prompt?
    Ex: Say I talk to customer care representative on internet bill, I did keep few sample questions and responses and now I expect the AI to answer more with context for which I need to fine tune.
    Thank you

    • @bigglocloud
      @bigglocloud 11 หลายเดือนก่อน

      try dialogflow

  • @metaleadership
    @metaleadership ปีที่แล้ว +1

    Can you download a tuned model for dev/testing on local machine?

    • @pat-grady-analytics
      @pat-grady-analytics ปีที่แล้ว +1

      is your local machine a super computer by chance?

    • @metaleadership
      @metaleadership ปีที่แล้ว +2

      @@pat-grady-analytics Nvidia DGX to run local models and training custom models.

    • @pat-grady-analytics
      @pat-grady-analytics ปีที่แล้ว +2

      @@metaleadership Lamda had this backend to train, "Our two submissions were benchmarked on 2048-chip and 1024-chip TPU v4 Pod slices, respectively. We were able to achieve an end-to-end training time of ~55 hours for the 480B parameter model and ~40 hours for the 200B parameter model."
      So I'm guessing your rig would take ~13-15 years to train the first model. You might be better off using the API

    • @metaleadership
      @metaleadership ปีที่แล้ว +1

      @@pat-grady-analytics Got it, lol

  • @camillorohe6996
    @camillorohe6996 ปีที่แล้ว

    Hey! After clicking the Fine Tuning button: There is a small loader but nothing happens..

    • @camillorohe6996
      @camillorohe6996 ปีที่แล้ว

      It was that infamous code: 13 error. After changing (literally) nothing it suddenly worked.

    • @camillorohe6996
      @camillorohe6996 ปีที่แล้ว

      Now I get: 0 token must inside [1, 1024]

    • @mohaiminshoron4911
      @mohaiminshoron4911 ปีที่แล้ว

      @@camillorohe6996 I have the same issue. the fine tuning doesnt start. were you able to solve the problem?

  • @abrarkhanniaziabrar7904
    @abrarkhanniaziabrar7904 ปีที่แล้ว +2

    Thanks I'm very happy with Google ۔

  • @Warung-AI-Channel
    @Warung-AI-Channel 8 หลายเดือนก่อน +1

    this is the reason why it's called Large Language Model (LLM) 🤪

  • @misbahuabubakar-o5p
    @misbahuabubakar-o5p 9 หลายเดือนก่อน

    Interested

  • @akashghosh4766
    @akashghosh4766 หลายเดือนก่อน

    You are❤

  • @سلويجبريل
    @سلويجبريل 4 หลายเดือนก่อน

    ❤❤❤

  • @erkancosan748
    @erkancosan748 ปีที่แล้ว

    Generative AI Studio

  • @reginaldooliveira0817
    @reginaldooliveira0817 ปีที่แล้ว +1

    Teach me about the matter master!? What time is it? Now! Where are you? Here. Help me please!

  • @sammyfrancisco9966
    @sammyfrancisco9966 3 หลายเดือนก่อน

    Is Nikita an AI generated character? Seems like it to me. No shade if it is a real person

  • @tegradetra
    @tegradetra ปีที่แล้ว

    What is your other language?

  • @DanielRodrigodaSilvaRodr-zl9ri
    @DanielRodrigodaSilvaRodr-zl9ri 5 หลายเดือนก่อน +1

    OI COMO ESTÁ VOCÊ TUDO BEM...❤😂🎉

  • @DuschiLudewig
    @DuschiLudewig 3 หลายเดือนก่อน

    Im meine Sprache,könnte ich verstehen,aber es ist leider nicht möglich........😍

  • @tijjanimusalambu6143
    @tijjanimusalambu6143 9 หลายเดือนก่อน

    I did not understand at all.