News for hackers. Stuff that matters.
Re:Ollama now supports AMD graphics cards by Abishek_Muthian on Saturday March 16, 2024 @05:10AM (#39724383)
For me all the projects which enable running & fine-tuning LLMs locally like llama.cpp, ollama, open-webui, unsolth etc. play a very important part in democratizing AI.

> what do you do after the initial experimentation? you need to deploy these models eventually to production

I built GaitAnalyzer[1], to analyze my gait laptop; I had deployed it briefly in production when I had enough credits to foot the AWS GPU bills. Ollama made it very simple to deploy the application, Anyone who has used docker before can now run GaitAnalyzer in their computer.

[1] https://github.com/abishekmuthian/gaitanalyzer

There are no comments on this comment yet.