Llama 3.2 Vision + Ollama: Chat with Images LOCALLY

Поделиться
HTML-код
  • Опубликовано: 30 ноя 2024

Комментарии • 50

  • @leonvanzyl
    @leonvanzyl  22 дня назад +6

    Thank you guys for the incredible support!
    Remember to like and subscribe to help this channel out 🙏

    • @BirdManPhil
      @BirdManPhil 19 дней назад

      Leon I need your expertise good sir

  • @rogerthao588
    @rogerthao588 22 дня назад

    Your tutorials are so helpful for me. Also, simply subscribing to you keeps me updated on new AI releases and tools. I learned about Flowise and Langflow from you. I also learned about the release of Llama 3.2 Vision (this video!) from you as well! Thanks!

    • @leonvanzyl
      @leonvanzyl  22 дня назад

      That's awesome to hear. Thank you

  • @Aureliusus
    @Aureliusus 17 дней назад

    Thank you for helping us getting started. You saved me quite some time on how to enhance my local llama with vision capabilities.

  • @chizzlemo3094
    @chizzlemo3094 22 дня назад

    super helpful. its quite incredible how lacking in notes and examples these models are when released, so thanks very much.

  • @BadBite
    @BadBite 22 дня назад

    very useful Leon, like everything you are posting! the best channel on the subject

  • @unokometanti8922
    @unokometanti8922 22 дня назад +4

    tried both 11b and 90b models. the 11b seems to be uncensored while the 90b is censored (first shortfall…); on top of that it looks like multimodal models cannot support parallel streams of actions (i.e. extract info from an img via OCR and then perform a search on the extracted contents); last but not least, they seem to be able to process only 1 img at a time….The resulting capabilities appear to be far behind “commercial” models. Unfortunately. Does anybody know if an uncensored version of a decent vision-enabled LLM has already been created?

  • @dgitalnarrative
    @dgitalnarrative 22 дня назад +1

    I would love to see a NextJS app with Ollama. Cherry on top would be agents looking into the images and categorizing them or something. Thank you for your amazing content @Leon

  • @TeamUnpro
    @TeamUnpro 19 дней назад

    Ty~ this will help greatly, was so tired of copypasting from a terminal lol

  • @leanprogrammer
    @leanprogrammer 22 дня назад +1

    nice! Nextjs ollama client would be really cool to see. i also wonder how good this model is with web design - convert design to code

  • @ShuaibShahzan
    @ShuaibShahzan 18 дней назад

    Thanks again for the great tutorial Leon. Please create a Next.js app.

    • @leonvanzyl
      @leonvanzyl  18 дней назад +1

      Will do

    • @ShuaibShahzan
      @ShuaibShahzan 18 дней назад

      @ Thanks Again Leon. Another idea for video is can we call one Agentflow/Chatflow from another Agentflow/Chatflow. The rationale behind this is to break complex flows into smaller flows.

  • @aykutylmaz9970
    @aykutylmaz9970 14 дней назад

    Which LLM can read pdf including mathematical functions shown in classical way (for example having integration symbols, dividing lines, squareroot symbols, etc.).I would appreciate your answer.

  • @tarassvystun466
    @tarassvystun466 22 дня назад

    Thanks for the video, I would like to see another video tutorial with a STREAMLIT

  • @angelochu3156
    @angelochu3156 19 дней назад

    Hi Leon, How much VRAM do you have on your computer to run this 9B vision model?

  • @rickyS-D76
    @rickyS-D76 22 дня назад

    Thank you, like to see integrate this model using Flowise ❤soon

    • @leonvanzyl
      @leonvanzyl  22 дня назад +1

      Oh, trust me. I'll definitely create a FW video on this

  • @ShaunyTravels.
    @ShaunyTravels. 22 дня назад

    Yes yes please build the app Leon !!!

  • @grahamharris7010
    @grahamharris7010 22 дня назад

    I hope this will be usable with LM studio eventually. Hello from a fellow SAfrican xD

    • @leonvanzyl
      @leonvanzyl  22 дня назад +1

      Howzit!
      I seriously need to create LMStudio videos as well

    • @grahamharris7010
      @grahamharris7010 22 дня назад

      @@leonvanzyl Oh yes! I have a cool multi AI agent chatroom running with an admin backend to control their convo and humans can partake in the chat. seriously believable chat agents and al running off Llama3.2 Instruct 3B and LM studio. Cheers on the content and subbed!

  • @Col-pd2zd
    @Col-pd2zd 17 дней назад +1

    Does Flowise allow us to use this with ollama chat?

    • @leonvanzyl
      @leonvanzyl  16 дней назад +1

      Not yet, but I think they'll release the feature SOON. Will create a video on it as soon as it's available.

  • @musumo1908
    @musumo1908 21 день назад

    Awesome! These GPU specs are restrictive though…I love openwebui but it runs like crap on older systems….

    • @leonvanzyl
      @leonvanzyl  21 день назад

      I would think that it would be similar to the terminal, no?

  • @lexbu6668
    @lexbu6668 22 дня назад

    Can we upload rar or zip files containing visual studio projects to write code? Can it read these files like chatgpt-4o ?

  • @themysteryman-e2j
    @themysteryman-e2j 4 дня назад

    What are minimum hardware requirements to get this running smoothly

    • @leonvanzyl
      @leonvanzyl  3 дня назад +1

      The image / multi modal models are resource intensive.
      I have a laptop with an RTX 4070 and the responses were not too slow.

    • @themysteryman-e2j
      @themysteryman-e2j 3 дня назад

      @leonvanzyl what about mac ?
      I want to buy mac for mL

  • @PedroLourenco-v4x
    @PedroLourenco-v4x 19 дней назад

    I installed 2 days ago but today im getting the following problem: zsh: command not found: ollama

  • @yacahumax1431
    @yacahumax1431 22 дня назад

    why all these vision model cant never ocr? I will think understanding text is easier.

  • @aayushpagare9366
    @aayushpagare9366 12 дней назад

    Can we chat with multiple images?

    • @leonvanzyl
      @leonvanzyl  12 дней назад +1

      Only one at a time

    • @aayushpagare9366
      @aayushpagare9366 12 дней назад

      @leonvanzyl hey I have a use case where I want to chat with multiple images do you have any suggestion ?

  • @ronschh
    @ronschh 22 дня назад

    Primer comentario