Run any AI model remotely for free on google colab

Поділитися
Вставка
  • Опубліковано 24 лис 2024

КОМЕНТАРІ • 92

  • @FilipeBento
    @FilipeBento 11 місяців тому +19

    Great stuff!!
    Ngrok is now asking for auth -- solved this by adding
    await asyncio.gather(
    run_process(['ngrok', 'config', 'add-authtoken',''])
    )
    before:
    await asyncio.gather(
    run_process(['ollama', 'serve']),
    run_process(['ngrok', 'http', '--log', 'stderr', '11434']),
    )

    • @lamechemohh9113
      @lamechemohh9113 11 місяців тому

      please i use windows how to use ngrok with him?

    • @FilipeBento
      @FilipeBento 11 місяців тому

      @@lamechemohh9113 you mean Ollama? You will need to run WSL2 (if you have any Win version that is not the Home edition).

    • @techwithmarco
      @techwithmarco  11 місяців тому +1

      Thanks a lot for adding this! Just pinned the comment

    • @techwithmarco
      @techwithmarco  10 місяців тому +2

      and by the way, I updated the github repository to reflect your proposals :)

    • @burncloud-com
      @burncloud-com 2 місяці тому

      @@techwithmarcoyou video is cool, I still have many question, can I contact you?

  • @SethuIyer95
    @SethuIyer95 10 місяців тому +5

    Thank you so much. I was killing my Intel mac with the LLM questions xD. This gives a good rest for it.

  • @techwithmarco
    @techwithmarco  Рік тому +2

    If you want to learn more about ollama.ai, head over to my initial video about it :)
    ua-cam.com/video/vUxAkCcag5s/v-deo.html

  • @d3mist0clesgee12
    @d3mist0clesgee12 11 місяців тому +2

    great stuff bro, keep them coming, thanks again.

  • @thoufeekbaber8597
    @thoufeekbaber8597 6 місяців тому +3

    Thank you.
    I could run this succesfully in the terminal, but how can access the model or the collab through jupyter notebook instance?

  • @jeffsanaraujo
    @jeffsanaraujo 10 місяців тому +3

    That’s a fantastic video! Do you know if Ollama has OpenAI API compliant endpoints? So we could use Google Colab as a “Backend-as-a-Service” for some time in our chatbots :) One way I saw people doing is to create a long audio (like 12 hours of audio), loading it in the Google colab, and giving it a play, it’s a silence audio. It seems to work to keep the session opened for more time.

    • @techwithmarco
      @techwithmarco  10 місяців тому +2

      There is currently an issue at the ollama gh project, so feel free to check that out and track the progress :)
      github.com/jmorganca/ollama/issues/305
      And good tip with the audio sound, never thought of that ... 😄

    • @tuliomop
      @tuliomop 10 місяців тому

      great tip

  • @iamderrickfoo
    @iamderrickfoo 5 місяців тому +1

    This is awesome stuff! Would like to know after this up can we connect this to Webui or Anythingllm?

  • @vijayamurugan271
    @vijayamurugan271 5 днів тому

    Thank you brother .it really helps.

  • @barskaracadag3923
    @barskaracadag3923 3 місяці тому +1

    Hi, I am jsut curious what is gonna happen once collab kicks us from using the gpu. Restart it all?

  • @Shivam-bi5uo
    @Shivam-bi5uo 10 місяців тому +4

    how do i save the progress, because everytime i run it, it downloads the model all from the start?

    • @WhyWouldHeSayThat
      @WhyWouldHeSayThat 10 місяців тому +1

      use your google drive bro, pay for 100gb. its worth it if you're an ai guy

  • @renega991
    @renega991 5 місяців тому +1

    Hi amazing stuff!
    Is there a way to connect the ngrok to jupyter notebook? Thanks!

  • @yanncotineau
    @yanncotineau 8 місяців тому +7

    i got a 403 forbidden error, but replacing
    run_process(['ngrok', 'http', '--log', 'stderr', '11434']) with
    run_process(['ngrok', 'http', '--log', 'stderr', '11434', '--host-header="localhost:11434"']) fixed it for me.

    • @tiagosanti3
      @tiagosanti3 8 місяців тому

      Fixed it for me too, thanks

    • @MR-kh8ve
      @MR-kh8ve 8 місяців тому

      for me worked too, thank you!

    • @nicholasdunaway2605
      @nicholasdunaway2605 8 місяців тому

      THANK YOU

    • @Kursadysr
      @Kursadysr 7 місяців тому

      You are a life saver!!!

    • @techwithmarco
      @techwithmarco  7 місяців тому

      great spot! I already updated the script on github :)

  • @mobilesales4696
    @mobilesales4696 3 місяці тому +1

    Tell me how can I add Tele-FLM-1T local llm model but directly install in Google colab and how host on server using Google colab and how can I put those address in any framework I mean how to configure it plz plz kindly tell me instructions plz I

  • @ralfrath699
    @ralfrath699 3 місяці тому +1

    I have win 10. How can I start the model?

  • @steelorigin
    @steelorigin Місяць тому

    Is there an updated video of this? I'm getting different end results and I'm not sure what is wrong? Where can I copy the code 1:1?

  • @mellio19
    @mellio19 8 місяців тому +1

    but can't run stable diffusion this way?

  • @Chadpritai
    @Chadpritai 7 днів тому

    It is really cool, how can add I open webUI features in so I can use cool colab gpu with it?

  • @QHawk7
    @QHawk7 2 місяці тому

    *Great! Thanks, can you do it with kaggle? , and with a local notebook/VSC?* Any update to this ?

  • @CharlesDubois-f7p
    @CharlesDubois-f7p 4 місяці тому +1

    How can I make this work with the ollama library in a python script? This works well when typing the prompts directly in the terminal, but my script still seems to run on my local instance.

    • @CharlesDubois-f7p
      @CharlesDubois-f7p 4 місяці тому

      For anyone running into the same issue, I figured it out. I had to set the environement variable in the script with os.environ["OLLAMA_HOST"] = ngrok_url BEFORE importing ollama

  • @SethuIyer95
    @SethuIyer95 10 місяців тому +2

    Thank you!

  • @omerfarukagtoprak2398
    @omerfarukagtoprak2398 3 місяці тому

    Thank you
    Wonderful video!!

  • @aryanflory
    @aryanflory 7 місяців тому +2

    hey, how to the export step on windows?
    I have the ollama installed

  • @jameschan6277
    @jameschan6277 4 місяці тому

    Please help if I use windows PC desktop, how can I open terminals like MAC?

  • @bennguyen1313
    @bennguyen1313 9 місяців тому

    I imagine it's costly to run LLMs.. is there a limit on how much Google Colab will do for free?
    I'm interested in creating a Python application that uses AI.. from what I've read, I could use ChatGPT4 Assistant API and I as the developer would incur the cost whenever the app is used.
    Alternatively, I could host a model like Ollama, on my own computer or on the cloud (beam cloud/ Replicate/Streamlit/replit)?
    As a 3rd option, could Google Colab work in my situation? Is OpenAI's Assistant API totally different from the API to programmatically interact with llama2 , mistral , etc?

  • @إضاءةذهبية
    @إضاءةذهبية 4 місяці тому

    very thanks,
    you help me alot!😍

  • @kunalbhooshan9667
    @kunalbhooshan9667 Місяць тому

    Can you add code for adding model from colabe rather then ollama

  • @attilavass6935
    @attilavass6935 9 місяців тому +1

    How can we keep our downloaded LLMs permanently, eg. on a mounted Google Drive?
    It would speed up the start of inference in a new ollama server start.

    • @techwithmarco
      @techwithmarco  8 місяців тому +2

      Yes, that's a brilliant idea! You can save those in google drive with this snippet for example:
      import os
      # Mount Google Drive
      from google.colab import drive
      drive.mount('/content/drive')
      # Create a folder in the root directory
      !mkdir -p "/content/drive/My Drive/My Folder"
      # Start Ollama with a path where models are stored
      OLLAMA_MODELS=/content/drive/My Drive/My Folder ollama serve

    • @attilavass6935
      @attilavass6935 8 місяців тому

      @@techwithmarco that's great, thank you! :)

  • @asdfg1346on
    @asdfg1346on 4 місяці тому

    can such a llm model be used in a web app not just in a terminal locally and how?

  • @pathsvivi
    @pathsvivi 6 місяців тому

    Thanks for the video. One question though, how can I avoid downloading the language models every time I run Colab notebook? Can I save Ollama and its models in Google drive and retrieve them when running the notebook?

  • @vg2812
    @vg2812 8 місяців тому +1

    Error: something went wrong, please see the ollama server logs for details
    am getting this error after running export OLLAMA_HOST= ...
    what should i do????

    • @techwithmarco
      @techwithmarco  7 місяців тому +1

      See the other latest comments or check out the new version on github. Should resolve the issue :)

    • @vg2812
      @vg2812 7 місяців тому

      @@techwithmarco okay I will check

    • @vg2812
      @vg2812 7 місяців тому

      @@techwithmarco thank you for the reply

  • @Codescord
    @Codescord 11 місяців тому +1

    can we just make it as api end point and create good frontend on top of it?

    • @techwithmarco
      @techwithmarco  11 місяців тому +1

      Yes, kind of. The url which is getting exposed via ngrok, it is also usable as url in front ends especially built for ollama.ai
      Check out my other ollama linked video, there I show how to start up a front end for that. (Last section)

  • @lamechemohh9113
    @lamechemohh9113 11 місяців тому +1

    Please what about windows user?

    • @techwithmarco
      @techwithmarco  11 місяців тому

      You can use ollama with WSL2, it is not available yet in windows

  • @DCS-um9oc
    @DCS-um9oc 6 місяців тому

    i got windows machine, do i need ollama locally tooo?

  • @AnonymousAccount514
    @AnonymousAccount514 2 місяці тому

    has this stopped working? have they caught on to us?

  • @abhishekratan2496
    @abhishekratan2496 8 місяців тому +1

    Very usefull video also the code
    btw i can't get it running on windows
    what would be the way to set OLLAMA_HOST variable on window
    set OLLAMA_HOST= "--" doesn't seem to work it still runs on local machine

    • @techwithmarco
      @techwithmarco  7 місяців тому

      I think it depends on the terminal and shell you are using. Are you using the standard windows terminal?

    • @TirthSheth108
      @TirthSheth108 7 місяців тому

      Hii @@techwithmarco , thanks for chiming in. I'm actually experiencing the same issue as @abhishekratan2496 , but I'm running it on the Ubuntu terminal. Setting the OLLAMA_HOST variable doesn't seem to work for me either. Any insights on how to resolve this would be greatly appreciated! Thanks.

    • @techwithmarco
      @techwithmarco  7 місяців тому

      @@TirthSheth108 Okay that's weird. I just used it a few days ago and it worked perfectly. I'll investigate and let you know :)

    • @AllMindControl
      @AllMindControl 6 місяців тому +1

      did anyone figure this out? it just tells me that export is not a recognized command

  • @harsh9558
    @harsh9558 11 місяців тому

    4:33
    The model is downloading on colab or locally?
    Also can u plz tell what command changes will be there if we are using windows terminal?

    • @techwithmarco
      @techwithmarco  11 місяців тому

      The model is being downloaded on the remote machine (colab)
      The commands stay the same, if you use WSL2 on windows with ollama.

  • @MultiverseMayhemtoyou
    @MultiverseMayhemtoyou 11 місяців тому +1

    This is Fire Can you help me connect open Interpretur Like this with So I can Give access to my computer But it wont load my PC that much

    • @py_man
      @py_man 10 місяців тому

      You can

  • @groshatc
    @groshatc 7 місяців тому

    awesome man

  • @AlexandreCastanet
    @AlexandreCastanet 10 місяців тому

    Good do you have idea to benmarch mixtral on colab ?

    • @techwithmarco
      @techwithmarco  10 місяців тому

      No sorry
      I am not that deep into AI stuff so that I know how to benchmark the performance 🥲

  • @stargate-s4
    @stargate-s4 6 місяців тому

    Found a Gem 💎

  • @AhmedEssam_eramax
    @AhmedEssam_eramax 11 місяців тому

    fantastic

  • @khushalsharma2031
    @khushalsharma2031 11 місяців тому

    Thanks for the video. You mentioned disconnecting the runtime. So I am assuming google will itself shut the running notebook in few hours. Do you know for how many hours continuously we can run this?

    • @techwithmarco
      @techwithmarco  11 місяців тому

      I just googled because I did not know, but apparently 90 minutes if you do not interact, or absolute 12 hours

    • @khushalsharma2031
      @khushalsharma2031 11 місяців тому

      @@techwithmarco so if we leave the server running colab tab ideal. I am assuming it will auto shut in 90 minutes.

    • @techwithmarco
      @techwithmarco  11 місяців тому +1

      Honestly I am not sure because I haven't used it for that long in one run.
      I would assume it will be up for 12 hours because the tunnel is working in the background and the jupyter notebook is still running :)

    • @clashgamers4072
      @clashgamers4072 11 місяців тому +1

      It will ask for are you a robot? captcha if you're inactive for a while , you could write a small javascript fn in browser to randomly click some ui elements but yeah 12 hours is the hardlimit after that you can't connect to a GPU instance for another day or so

  • @thepsych3
    @thepsych3 8 місяців тому

    i get error like 403 forbidden

    • @ricardomorim9444
      @ricardomorim9444 8 місяців тому +1

      replace:
      run_process(['ngrok', 'http', '--log', 'stderr', '11434']) with
      run_process(['ngrok', 'http', '--log', 'stderr', '11434', '--host-header="localhost:11434"'])
      That fixed it for me.

    • @paulopatto8283
      @paulopatto8283 7 місяців тому

      @@ricardomorim9444 tkx very much guys, solved my issue.

  • @asir9129
    @asir9129 3 місяці тому

    Missed opportunity to say "say less" as supposed to "say no more", I think it sounds funnier

    • @techwithmarco
      @techwithmarco  2 місяці тому

      I really don't get it as I am not a native speaker 😂