Run any AI model remotely for free on google colab

Подписаться 2,5 тыс.

Просмотров 17 тыс.

50% 1

🦙 Installing ollama.ai on google colab with Ease! 🎉
In this video, I'll show you how to easily run ollama.ai and other large language models (LLMs) remotely using the handy platform 'Google Colab'.
Say goodbye to having not enough compute power to run your dream ai model! 🚀
We use Ngrok, to expose our ollama server from the colab server to the internet. Ngrok is a software which allows you to create secure tunnels and expose local ports to the internet.
🔧 What is Ollama?
• Ollama.ai to install l...
Ollama is an open source tool that simplifies the installation process of Llama2 and other large langue models (LLMs). It provides an easy-to-use interface for installing llms on your system, without requiring you to manually configure
any dependencies or settings. With Ollama, you can quickly and easily get started with Llama2 in just a few minutes! 🚀
📔 Jupyter Notebook
github.com/marcogreiveldinger...
📝 Installation Steps
In this video, I'll walk you through the step-by-step process of installing ollama on google colab with a python jupyter notebook. From downloading the tool to running your first remote AI, I'll cover it all! 💻
🎬 Watch and Learn
Whether you're a seasoned AI user or just getting started, this video is perfect for anyone looking to install and use LLMs remotely without any privacy concern.. So sit back, relax, and let me
guide you through the process of using google colab with Ollama! 😊
00:00 - 00:42 Introduction
00:43 - 03:21 google colab coding
03:22 - 04:14 start your jupyter notebook
04:15 - 06:34 link your local machine to the remote host
06:35 - 07:10 Outro
🔗
VIdeo is based on the example provided by ollama: github.com/jmorganca/ollama/t...
github.com/marcogreiveldinger...
ollama.ai
colab.google/
ngrok.com/
#googlecolab #ollama #ollamaai #privateAI #chatgpt #privategpt

Наука

Опубликовано:

3 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 82

@FilipeBento 7 месяцев назад

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 7 месяцев назад

please i use windows how to use ngrok with him?

@FilipeBento 7 месяцев назад

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

@techwithmarco 7 месяцев назад

Thanks a lot for adding this! Just pinned the comment

@techwithmarco 6 месяцев назад

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

@d3mist0clesgee12 7 месяцев назад

great stuff bro, keep them coming, thanks again.

@techwithmarco 7 месяцев назад

Thanks! I will :)

@omerfarukagtoprak2398 6 дней назад

Thank you Wonderful video!!

@SethuIyer95 7 месяцев назад

Thank you!

@SethuIyer95 7 месяцев назад

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

@techwithmarco 7 месяцев назад

Perfect!

@user-dh9ez3mf7c 8 дней назад

very thanks, you help me alot!😍

@iamderrickfoo 2 месяца назад

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

@thoufeekbaber8597 3 месяца назад

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

@user-em7se7bm7v 3 месяца назад

awesome man

@AhmedEssam_eramax 7 месяцев назад

fantastic

@renega991 Месяц назад

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

@jeffsanaraujo 7 месяцев назад

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 7 месяцев назад

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 6 месяцев назад

great tip

@bennguyen1313 5 месяцев назад

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?

@pathsvivi 2 месяца назад

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?

@shrishubhyadav05 2 месяца назад

Found a Gem 💎

@mellio19 4 месяца назад

but can't run stable diffusion this way?

@DCS-um9oc 2 месяца назад

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

@asdfg1346on 25 дней назад

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

@AfnanQasim-wk8nq 2 месяца назад

canw e load 70B model with this same technque ?

@jameschan6277 15 дней назад

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

@harsh9558 7 месяцев назад

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 7 месяцев назад

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

@Shivam-bi5uo 6 месяцев назад

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

@lewybagz 6 месяцев назад

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

@mobilesales4696 2 дня назад

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

@Codescord 8 месяцев назад

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

@techwithmarco 8 месяцев назад

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)

@aryanflory 4 месяца назад

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

@biological-machine 2 месяца назад

just use "set OLLAMA_PATH=the_url"

@khushalsharma2031 8 месяцев назад

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 8 месяцев назад

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

@khushalsharma2031 8 месяцев назад

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

@techwithmarco 8 месяцев назад

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 7 месяцев назад

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

@attilavass6935 5 месяцев назад

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 4 месяца назад

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 4 месяца назад

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

@CharlesDubois-f7p 20 дней назад

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 20 дней назад

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

@AlexandreCastanet 6 месяцев назад

Good do you have idea to benmarch mixtral on colab ?

@techwithmarco 6 месяцев назад

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

@MultiverseMayhemtoyou 8 месяцев назад

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 6 месяцев назад

You can

@lamechemohh9113 7 месяцев назад

Please what about windows user?

@techwithmarco 7 месяцев назад

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

@vg2812 4 месяца назад

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 4 месяца назад

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

@vg2812 4 месяца назад

@@techwithmarco okay I will check

@vg2812 4 месяца назад

@@techwithmarco thank you for the reply

@abhishekratan2496 4 месяца назад

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 4 месяца назад

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

@TirthSheth108 4 месяца назад

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 4 месяца назад

@@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 3 месяца назад

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

@thepsych3 4 месяца назад

i get error like 403 forbidden

@ricardomorim9444 4 месяца назад

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 3 месяца назад

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

@techwithmarco 8 месяцев назад

If you want to learn more about ollama.ai, head over to my initial video about it :) ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-vUxAkCcag5s.html

@yanncotineau 4 месяца назад

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.