Ollama-Run large language models Locally-Run Llama 2, Code Llama, and other models

[@vishalnagda7]

I'm feeling lucky that I got this video in my suggestions.

[@divyaramesh3105]

Thank you Krish sir. In Building RAG from scratch ,sunny sir showed about Ollama. Both of you were giving foundational knowledge and updates in GenAI. It was very useful sir.

[@devanshgupta6064]

please give sunny sirs youtube @

[@divyaramesh3105]

​@@devanshgupta6064 @sunnysavita10

[@sailikitha8502]

Sunny Savita @sunnysavita10

[@neerajshrivastava5600]

Krish, Fantastic Video and great explanation!!! Keep it up

[@mehdi9771]

We need a long versions videos like previously and thanks for your efforts ❤

[@sarimali8853]

Very good explanation, I have question can I train this model for specific taks mean features extraction or others?

[@SomethingSpiritual]

why ollama not taking full gpu? its taking full cpu only, pls guide

[@manjeshtiwari7434]

Thank You so much for a such a great video , I have a query , I am getting very slow response does the speed of response depends on system config , I have chekced out system use and while running it isn't using much resource , can you tell how can we increase response speed

[@rajendarkatravath2207]

Thanks krish! for sharing this knowledge . what an amazing model it is .....!

[@NISHANTKumar-ct3pb]

Thanks , it's great video. Wanted to ask when we say local what is the configuration of local is it a cpu or GPU based system? Are models compressed / quantized or same as original ? Is there a model size limitation vs local system config?

[@kenchang3456]

Hey Krish, thanks for doing this video in Windows.

[@Shrieenidhi]

If the model is installing locally means, will it take space of the RAM?

[@lionelshaghlil1754]

Thanks Krish, the briliant, innovative and master of the AI 😊, I have a question please related to the hosting, so assume I'd like to implement my solution on a server, will I need to have both, OLAMA and my app in two seperate dockers? they would communicate together? or they could be implemented in one single docker?

[@krishnaik06]

It can be implemented in one docker

[@ayushmishra5861]

Have you got clarity on the same, can you please share.

[@roshanchandel7929]

The heroes we need!!

[@usingsk]

Thanks for Sharing knowledge. Can we fine tune with company domain content in downloaded model and the data is not shared. I mean it comply with IPR if we use locally

[@BelhsanMohamed]

as always thanks for the information

[@jacobashwinmathew3763]

Can you make a complete video of production ready open source LLM basically LLMOps

[@deeks_edits]

You are the best!🤓

[@krishnaprasadsheshadri6206]

Can we get a video about reading tables using unstructured and such frameworks

[@sawankumar2088]

Can we just download and use or do we require any meta-ai api key as well?

[@ankitshaw2011]

Thankyou so much for these videos

[@tharunps8048]

Since it is running locally, using this model with organization's data doesn't expose it right ?

[@nagasudha6928]

Hi Krish This is Sudha from ISRO Hyderabad, I would like to know the documents to be provided for ollama and get the answers from it

[@shashank046]

Hi, how do I use gpu on open web ui? My model response is really slow and is not using gpu even though is used the command for using gpu for installing as mentioned on the open web ui GitHub page ..

[@susnatakanjilal703]

Sir I need to create a custom text data set from common crawl.for Bengali language....and train llama2 using that...can you plz demonstrate similar project!?

[@sanjaynt7434]

Can this read a document and answer my questions on that document can it.

[@YashDeveloper-rq2yc]

Bro using these techniques can I convert it as superb ai assistant? And what capabilities can use?

[@ranemghalion581]

thankyou

[@VishalTank-vk5ju]

Hello, krish, I am facing an issue with the Ollama service. I have an RTX 4090 GPU with 80GB of RAM and 24GB of VRAM. When I run the Llama 3 70B model and ask it a question, it initially loads on the GPU, but after 5-10 seconds, it shifts entirely to the CPU. This causes the response time to be slow. Please provide me with a solution for this. Thank you in advance. Note:- GPU load is 6-12 % and CPU load is 70% .

[@AjayYadav-xi9sj]

Make a video on Python framework of ollama. Make a end to end project and also host it somewhere where real people can use it

[@kashishvarshney2225]

hello sir, what is the minimum system configuration for ollama

[@parthwagh3607]

Thank you so much krish. I am having problem running models downloaded from hugging face having safetensor file. I have these files in oobabooga/text-generation-webui. I have to use this for ollama. I followed everything, even created modelfile with path to safetensor directory, but it is not running >> ollama create model_name -f modelfile. Please help me.

[@rajarshidey424]

How can we get the code?

[@pssab8]

Excellent videos. I set up mistral model locally on ubuntu20.04 and found that it is taking more than a minute for every response .Running in cpu mode only.Can you suggest me to improve the performance.

[@amazingedits9298]

This models are running on your computer hardware.So it requires a good hardware like gpu or something for creating quicker responses

[@KumR]

Do we need to download the entire 7gb llama2 locally to use with ollama

[@NeelamDevi-z6e]

Great content Krish...Need these coding files kindly share those

[@manasjohri2495]

Can you please tell me how we can run this ollama on GPU right now it is working on CPU?

[@ashishdayal172]

hii krish, i am facing error creating modelfile .Please help

[@hassanahmad1483]

How to deploy these custom gpts...?

[@naveenkumarmaurya3182]

hi krsih i m getting this error Ollama run codella! 🐰💨 (Note: I'm just an AI, I don't have personal preferences or the ability to run code, but I can certainly help you with any questions or tasks you may have!)

[@VishalKumar-gv6gy]

Does it require GPU ?

[@Nagireddy-lw7rl]

Hi Krish sir I have need ollama chatbot python code provide me. I check with your Github.

[@YashDeveloper-rq2yc]

After installing it will work in offline?

[@krishnaik06]

Yes

[@YashDeveloper-rq2yc]

@@krishnaik06 Thanks for sharing quality content

[@rishiraj2548]

🙏💯👍

[@jatinchawla1680]

llm=ollama(base_url='localhost:11434',model="llama 2") TypeError: 'module' object is not callable Can someone pls help w this?

[@kavitajakkali5030]

I Installed ollama in my local system but getting responses is taking very long time what can i do for that one ?

[@omarnahdi3380]

Hey sir😄, please make a video on BioMistral( a LLM trained on Medical and Scientific Data). It would perfectly fit your AI Nutriationist. Thanks for your daily dose of GenAI

[@starkgaming1425]

Please release a step by step guide on how to fine tune Gemini API in Python.....I tried by refering to documents but encountered a lot of errors with OAuth Setup please...........!!!

[@nasiksami2351]

Great tutorial! Can you please make a video on finetuning model on custom csv dataset and integration with Ollama. For instance, consider I have class imbalance problem in my dataset. Can I finetune a model, then ask it in Ollama, to generate more samples of minority class using the finetuned model?

[@copilotcoder]

Sir please create a codebase understanding model using ollama and test it on a opensource codebase

[@mohammedalfarsi4361]

are these model support arabic language ?

[@AjaySharma-jv6qn]

Content is helpful, thanks for your effort.🎉

[@durgakorde3589]

R u a data scientist?

[@velugucharan8096]

Sir please complete the fine tuning llms playlist as much as possible sir

[@DeadJDona]

please finish that Chrome update 😢

[@computerauditor]

Really insightful krish!!

[@marcoaerlic2576]

Thanks for the video.

[@haritdey430]

Nice video sir

[@MotoEdge40-j3v]

Every time we see a kid we ask him to say a poem and when you have so many llm models but you only want a poem on machine learning