Your Computer, Your Models, Your Rules - Transformer Lab

แชร์
ฝัง
  • เผยแพร่เมื่อ 9 ก.พ. 2025
  • Ali and Tony demonstrate the power of Transformer Lab, an open-source platform that allows anyone to build, tune, and run LLMs locally, without writing code.
    Learn more: transformerlab.ai
    Get the code: github.com/tra...
    Mozilla Builders helps developers create transformative open-source AI projects through collaborations, programming, and community. Check out the projects we’re supporting: builders.mozil...

ความคิดเห็น • 60

  • @modolief
    @modolief วันที่ผ่านมา +8

    2:23 - Start here (skip intro)

  • @NilasScweisthal
    @NilasScweisthal 4 วันที่ผ่านมา +17

    Looks like I stumbled on a treasure trove. Very nice thanks you for that

  • @szebike
    @szebike 2 วันที่ผ่านมา +6

    Excellent , you did open source a very good service thank you for the effort!

  • @owcsc
    @owcsc 21 ชั่วโมงที่ผ่านมา

    OPEN-SOURCE RULES!!!🎉 Thank you TransformerLabs!❤

  • @soccerkenshin
    @soccerkenshin 5 วันที่ผ่านมา +4

    This team is on 🔥🔥! Keep it up

  • @PhilEhI
    @PhilEhI วันที่ผ่านมา +1

    This looks fantastic!

  • @Drone256
    @Drone256 วันที่ผ่านมา +2

    You said you were fine tuning the base model, but you somehow magically ended up with a fine tuned instruct model. Are you sure you aren’t fine tuning the instruct model?

  • @ricka4678
    @ricka4678 2 วันที่ผ่านมา

    This is awesome, I will be testing it out

  • @TerragonAI
    @TerragonAI 2 วันที่ผ่านมา

    great !!! i will try out this weekend 🙂

  • @Qamar92
    @Qamar92 3 วันที่ผ่านมา +1

    Exactly what i need. thanks

  • @UntoldMagazineChannel
    @UntoldMagazineChannel 4 วันที่ผ่านมา

    Love it! Great job

  • @Juan-n6k3c
    @Juan-n6k3c วันที่ผ่านมา

    Wow this is great!

  • @chatbotte1838
    @chatbotte1838 4 วันที่ผ่านมา +2

    stopped with errors, while install torch==2.5.1, macos 12.7.6
    not for me :(

    • @brunopanizzi
      @brunopanizzi 14 ชั่วโมงที่ผ่านมา

      Create an issue at the repo, it is open source

  • @brandonhamaguchi
    @brandonhamaguchi 5 วันที่ผ่านมา

    Hi, I installed it on my Windows 11 PC, it says that I need to install "WSL", I search that, and the Microsoft page says that I have to run the command wsl --install, I did that and seems to be done ok. But when opening the app is still saying that I need WSL (I uninstalled and installed the app again and have the same issue). The app version that I installed is 0.9.3.
    Any help on how I can get the app running? Thanks!

    • @DoppsPkin
      @DoppsPkin 3 วันที่ผ่านมา

      same, wsl is installed and active

    • @917439
      @917439 3 วันที่ผ่านมา +2

      Did you try rebooting

    • @TomM-p3o
      @TomM-p3o 2 วันที่ผ่านมา

      ​​@@917439😂
      So true, rebooting solves 95% of the issues

    • @brandonhamaguchi
      @brandonhamaguchi 2 วันที่ผ่านมา

      @@917439 yes

    • @repica8034
      @repica8034 2 วันที่ผ่านมา +1

      you probably need to add a linux distribution to your wsl, ubuntu 24.04 LTS should be good and can be directly downloaded from the microsoft store, reboot after that to make sure it's installed properly

  • @TomM-p3o
    @TomM-p3o 2 วันที่ผ่านมา

    This is interesting, however I've been told that fine-tuning modern models can be a delicate process that might have to be customized for each model. How is this achieved?

  • @sammcj2000
    @sammcj2000 2 ชั่วโมงที่ผ่านมา

    Ironically I just tried transformer lab and the first issue I hit was python package and versioning issues.

  • @TalsBadKidney
    @TalsBadKidney วันที่ผ่านมา +1

    "You've probable seen a wall of python errors like this one" every single day, buddy

  • @user-dm5qi4nb6l
    @user-dm5qi4nb6l 2 วันที่ผ่านมา

    I want a way to train a small model that is already good in like language translation, math or programming and improve them on that field for example give it a whole new documentation on x framework, I could just scrape it ask ai to generate the test rewards etc, the data to be trained on based on the documents provided and then just go, test itself and self improve

  • @oneofpro
    @oneofpro 4 วันที่ผ่านมา

    Thanks

  • @dubyeh5243
    @dubyeh5243 2 วันที่ผ่านมา

    Nice!

  • @TudorAdrian
    @TudorAdrian วันที่ผ่านมา

    Sooooooo cool!

  • @elubaloops
    @elubaloops วันที่ผ่านมา +1

    guess again going on the odd direction AI is eating UI but it's cool like for now it's great really

  • @Edmund-b9q
    @Edmund-b9q 2 วันที่ผ่านมา +1

    Write it in c++

    • @TheMaxAwesome
      @TheMaxAwesome 2 วันที่ผ่านมา

      Write in Rust, you cowards!

    • @Edmund-b9q
      @Edmund-b9q 2 วันที่ผ่านมา

      @@TheMaxAwesome never

    • @jondoe6608
      @jondoe6608 วันที่ผ่านมา

      Write it in anything that is not python, I'd love C, C++ or Rust :D

  • @MomenRashad
    @MomenRashad วันที่ผ่านมา

    woow cool

  • @rocks7172
    @rocks7172 5 วันที่ผ่านมา

    cool

  • @skit555
    @skit555 2 วันที่ผ่านมา

    1B non-specialized are not worth massively deploying yet 😕

    • @jondoe6608
      @jondoe6608 วันที่ผ่านมา +1

      But they are getting better, its nice to see the tooling get developed and it will be ready when small LMs are ready.

    • @geekinthefield8958
      @geekinthefield8958 วันที่ผ่านมา

      Most people NEED specialized models with a generalized base. They don’t actually need a fully generic model, just enough to get a good set of navigational language around a particular domain.
      Tools like this or IBM’s InstructLab are great for models that companies want to use in-house.

  • @TellyT-i5e
    @TellyT-i5e 23 ชั่วโมงที่ผ่านมา

    Mac users don’t know how to full screen an app so now I’m having to squint. Smh

  • @alexsov
    @alexsov วันที่ผ่านมา

    Qwen2? How old is your presentation?

  • @TimothyHuey
    @TimothyHuey 2 วันที่ผ่านมา +11

    So, the only way an LLM can learn a subject you want to teach it is Q&A? Seems tedious and unnecessary. Why not just give it a set of PDFs, Webpages, Official Documentation, Rule guides, Governmental references etc. If you have to teach it by giving it the answer to every single possible query and permutation of that query, you will be training for a lifetime on something as simple as a sports game.

    • @illegalcall
      @illegalcall วันที่ผ่านมา

      Yes exactly my question

    • @ckpioo
      @ckpioo วันที่ผ่านมา +9

      because the raw data within PDFs, webpages, docs, etc fundementally has no meaning, you need to understand that training an LLM is like trying to teach an alien baby about humans, you NEED to provide a clear concrete relationship which is a q -> a relationship.
      if you were to train an llm just on raw data without any relationships then it will only memorize what's written on it and would know nothing about what any of it means

    • @glyph6757
      @glyph6757 วันที่ผ่านมา +7

      LLMs don't need to be trained on questions and answers. However, because LLMs work by predicting the next token (fragment of a word) then when an LLM that has not been trained on questions and answers is asked a question by a human the tokens that an LLM might respond with might not be what we consider an answer, much less what we could consider a good answer.
      So the best way we've found to increase the likelihood that an LLM answers with a good answer is to train it on questions and good answers.

    • @Japneets1
      @Japneets1 8 ชั่วโมงที่ผ่านมา

      Teaching on QnA is supervised fine tuning. Teaching next word prediction on pdfs is pre training. There is a difference for a reason. SFT is needed so that LLM can answer in QnA format.

    • @j1rosdream
      @j1rosdream 7 ชั่วโมงที่ผ่านมา

      If you don't want your model to just output random blurbs of text your need to train it on completely intact and grammatically correct samples, otherwise it could just stop talking in the middle of a

  • @MrRavaging
    @MrRavaging 2 วันที่ผ่านมา

    Yeah, Python sucks. That's why I switched to Rust, C, and R.

  • @HappyDancerInPink
    @HappyDancerInPink 2 วันที่ผ่านมา +1

    4:10 as per usual, local llms suck.

  • @justafreak15able
    @justafreak15able วันที่ผ่านมา

    Bro fix your browser first

  • @Graveness4920
    @Graveness4920 วันที่ผ่านมา +2

    As always, you are focusing on the wrong problem. You should have spoken with a domain expert first to gain a proper understanding. I hope my donation didn’t go toward funding you two.

    • @johnefan
      @johnefan วันที่ผ่านมา +2

      Maybe, interested to know what the right problem is?

    • @lovol2
      @lovol2 วันที่ผ่านมา

      So please do elaborate

    • @geekinthefield8958
      @geekinthefield8958 วันที่ผ่านมา

      All snark and no substance, try to give us something useful instead of generic LLM snobbery.