Fine Tuning Large Language Models with InstructLab

แชร์
ฝัง
  • เผยแพร่เมื่อ 7 ม.ค. 2025

ความคิดเห็น • 36

  • @khairullahhabib3982
    @khairullahhabib3982 26 วันที่ผ่านมา

    Very good delivery! I can watch this guy explain stuff all day. Keep it up! I can't believe all this knowledge is just free out here

  • @volkovolko
    @volkovolko 4 วันที่ผ่านมา

    Great Tool, I was waiting a full well made video of this tool and here it is !
    A collab notebook would be great if possible 😉

  • @cloudnativecedric
    @cloudnativecedric หลายเดือนก่อน +1

    Many thanks for the opportunity!

  • @murunatan6661
    @murunatan6661 หลายเดือนก่อน +3

    This is really good. Easy to understand and implement.

  • @taygundogan
    @taygundogan หลายเดือนก่อน +2

    Yeeeey Cedric, more videos from Cedric please please!!

  • @stanTrX
    @stanTrX 28 วันที่ผ่านมา +3

    Thanks. Does it work the same with ollama?

  • @learnbydoingwithsteven
    @learnbydoingwithsteven หลายเดือนก่อน +1

    Very clear. Gonna try it.

  • @AmeerHamza-cy6km
    @AmeerHamza-cy6km หลายเดือนก่อน +2

    how can I train it on PHP programming language, and some php projects.

    • @aganithshanbhag
      @aganithshanbhag 29 วันที่ผ่านมา +1

      question answer set (vast training material on php programming)

  • @gokcerbelgusen1062
    @gokcerbelgusen1062 หลายเดือนก่อน +1

    I will try this, thank you

  • @andrewcameron4172
    @andrewcameron4172 หลายเดือนก่อน +1

    What version of ilab were you running in this demo?

    • @cloudnativecedric
      @cloudnativecedric 29 วันที่ผ่านมา

      Ah, so this was InstructLab v.17 when we recorded :)

  • @maneeshs3876
    @maneeshs3876 หลายเดือนก่อน +1

    Nice video !

  • @justwanderin847
    @justwanderin847 หลายเดือนก่อน +2

    I was just wondering how they really train AI. This helps.

  • @nadoiz
    @nadoiz 11 ชั่วโมงที่ผ่านมา

    You say that you have to link the data you created to a GitHub link, and then a pull is done. Is this mandatory?

  • @PB-kx4vv
    @PB-kx4vv 28 วันที่ผ่านมา

    InstructLab presentations lead me to fantasize about training a model to shorten the learning curve for large open source projects. For example, the code-aster finite element package, with huge amounts of documentation and many documented test cases can many structural and dynamic and even thermal mechanical systems. However, the combinations of features which work compatibly with each other feels to a beginner like a fractal landscape. It is ok to go through an example, but it is easy to loose footing at near adjacencies. It would be nice to talk to a model about strategies to construct a new model, which can reference particular documents and examples, and identify prospective strategies as self conflicting. But when I imagine mapping this problem to instruct lab, I imagine it to be a more daunting task than just working with the program and gaining experience, and reading a lot.

  • @ZakinAbdul
    @ZakinAbdul หลายเดือนก่อน +2

    That was awesome, and I was wondering, can we fine-tune that model with an RAG chatbot-like, chat with it and feed it new info through our chats?

  • @ml00000
    @ml00000 หลายเดือนก่อน +1

    Excellent presenter!

  • @광광이-i9t
    @광광이-i9t 11 วันที่ผ่านมา

    Thanks!!

  • @ajaykumarpandey7327
    @ajaykumarpandey7327 6 วันที่ผ่านมา

    Which laptop is being used here

  • @gauravmodi12
    @gauravmodi12 15 วันที่ผ่านมา

    How much data it need to do proper fine tuning ?

  • @rajavemula3223
    @rajavemula3223 22 วันที่ผ่านมา

    Can fine tuning can be done with cpu? I mean without gpu?

  • @LoVe-iu9rd
    @LoVe-iu9rd 19 วันที่ผ่านมา

    May I know what is your laptop spec?

  • @munawwarkhan1926
    @munawwarkhan1926 หลายเดือนก่อน +1

    This is a great video and a good intro to an amazing tool. Just one suggestion, it does need some knowledge and background of computer science and data structures. I don't think it is for people with zero knowledge or background as the video suggestsin the beginning. Amazing content IBM, learning a lot here.

    • @cloudnativecedric
      @cloudnativecedric หลายเดือนก่อน

      Thank you very much for the feedback! That is true, there are some basics that are helpful in doing this, as well as terminal usage skills, but what we're working on as well is a user interface for the upstream InstructLab project, so it's essentially a simple form to include Q&A pairs, source documents, and attribution! Then the rest of the process like data generation and training is automated :)

    • @Pregidth
      @Pregidth 28 วันที่ผ่านมา

      @@cloudnativecedric If I understand correctly, by providing exact Q&A pairs during the fine-tuning process, we are effectively guiding the LLM to produce specific, deterministic answers to certain questions. Does this mean we are reducing the inherent randomness in the answers that LLMs typically generate based on their pre-trained weights? If so, wouldn’t this approach limit the model’s flexibility to incorporate its broader pre-trained knowledge into the context of the fine-tuned domain?

  • @george_davituri
    @george_davituri หลายเดือนก่อน +1

    impressive, need to try cool stuff

  • @jacquesgastebois
    @jacquesgastebois หลายเดือนก่อน +1

    I want to do the same with a tiny model please

    • @vdpoortensamyn
      @vdpoortensamyn หลายเดือนก่อน

      Our Granite models are quite tiny. 😊

  • @activewire-web5710
    @activewire-web5710 17 วันที่ผ่านมา

    What about hallucinations or guardrails

  • @nazarmohammed5681
    @nazarmohammed5681 11 วันที่ผ่านมา

    Plz share the Github repo

  • @philtoa334
    @philtoa334 หลายเดือนก่อน +1

    Nice.

  • @godfather_2001
    @godfather_2001 10 วันที่ผ่านมา

    Kate Winslet, Anne hathaway 🤭

  • @NhatNguyen-bq6jj
    @NhatNguyen-bq6jj 15 วันที่ผ่านมา

    Quantum AI