Ollama Now Officially Supports Llama 3.2 Vision - Talk with Images Locally

Поділитися
Вставка
  • Опубліковано 28 лис 2024

КОМЕНТАРІ • 35

  • @fahdmirza
    @fahdmirza  22 дні тому +1

    🔥How to Upgrade Ollama Version in Linux Windows and Mac - ua-cam.com/video/338CNrJgN08/v-deo.htmlsi=a8FWgEqzPOPQ8pBn

  • @xw33b36
    @xw33b36 22 дні тому +7

    Woo! lets goo! I forked a copy of open-webui to use clip for all image uploads so any model could parse images but this will be so much easier. just need bigger vision models now! 11b still so tiny. Also, Fahd, you are truly my favorite machine learning youtuber. Can you do us a video soon with 5 best LLM and multi-modal LLM's right now?

    • @xw33b36
      @xw33b36 22 дні тому +3

      Also my friend, have you done a video on deepspeed? It would be interesting to see how people could make use of it to create cuda nodes on local network from multiple machines.

    • @fahdmirza
      @fahdmirza  22 дні тому +3

      Sounds great! and sure, I will look into best LLM video, though it changes so rapidly the shelf life would be so little. Also thank you for the Super Thanks. You just made my day.

  • @enricollen
    @enricollen 17 днів тому

    Thanks ❤

  • @Mnbir
    @Mnbir 22 дні тому +3

    Thanks

    • @fahdmirza
      @fahdmirza  22 дні тому +2

      Thanks a ton for Super Thanks. Much appreciated 🙏

  • @bossgd100
    @bossgd100 21 день тому +1

    The LLM answers are fast, what GPU are you using ?

    • @fahdmirza
      @fahdmirza  21 день тому

      I mentioned that in the video. thanks

    • @bossgd100
      @bossgd100 21 день тому

      @fahdmirza I will watch it again more carefuly thank you. I am not native english speaker

    • @fahdmirza
      @fahdmirza  21 день тому

      @@bossgd100 thank you, let me know if you cannot find it, I will fish it out for you.

  • @andrepaes3908
    @andrepaes3908 22 дні тому +2

    What's the maximum resolution of pics you can upload in the model?

    • @fahdmirza
      @fahdmirza  22 дні тому +3

      1120x1120 pixels

    • @ajarivas72
      @ajarivas72 21 день тому

      ​@@fahdmirza your videos are awesome

    • @andrepaes3908
      @andrepaes3908 20 днів тому

      @@fahdmirza Wow that's pretty good! thanks for the reply!

  • @roshanYadav-y8f
    @roshanYadav-y8f 19 днів тому

    I have nvidea Rtx 3050 can i use

  • @alejandrof9816
    @alejandrof9816 21 день тому

    Thanks for the video! I've tried Llama3.2 vision on AnythinLLM but even though the chat works, the vision doesn't seem to recognize any images. Do I need any extra configuration?

    • @fahdmirza
      @fahdmirza  21 день тому +1

      yes you need to fine-tune on a pertinent dataset

    • @alejandrof9816
      @alejandrof9816 21 день тому +1

      @fahdmirza I'll keep that in mind, thanks for the reply!

  • @bossgd100
    @bossgd100 21 день тому +1

    Can you create a bot from it ? like a game bot that click and type in a web browser game ?

  • @alisaid3745
    @alisaid3745 19 днів тому

    Its cutoff date is December 2021 means 3 years.
    Looking a module its cutoff date on 2024

  • @saadirfan2358
    @saadirfan2358 22 дні тому

    When will ollama support tti ?

    • @fahdmirza
      @fahdmirza  21 день тому

      thats the question for ollama team :)

  • @fineCoder.
    @fineCoder. 21 день тому

    can I run this in 1650 (16 gigs)

  • @ShaunyTravels.
    @ShaunyTravels. 22 дні тому

    Ok thats great but what about a image containing text?

    • @fahdmirza
      @fahdmirza  21 день тому

      I have similar videos on the channel, please search, thanks

  • @viangelo4z595
    @viangelo4z595 21 день тому

    my gpu is dead

    • @fahdmirza
      @fahdmirza  21 день тому +1

      how much vram you have

    • @viangelo4z595
      @viangelo4z595 21 день тому

      @fahdmirza The total ram of my computer is 32 🥲

    • @fineCoder.
      @fineCoder. 21 день тому

      can i run this in 16 gigs 1650