That’s very exciting! Instead of calling copilot or perplexity.ai and telling all the world what you are after, you can now host similar service on your own PC or laptop!

Recently we have seen several new LLMs were released. Exciting times. Let’s test and see how they perform when detecting logical fallacies.

When I started experimenting with LLMs the UIs for them were in active development and now some of them are really good.

Still there are some common approaches how to write good prompts so LLM would not get confused trying to understand what you wand from it.

I’ve tried different tools and came to conclusion I like floccus the most.

Sometimes need this but can’t find rightaway. So keeping them all here.

When I trained object detector AI some time ago - LabelImg was a very helpful tool, but the export from Label Studio to COCO format wasn’t accepted by MMDetection framework..

Testing how models with different number of parameters and quantization are behaving.

After installing ollama better to reconfigure ollama to store them in new place right away. So after we pull a new model, it doesn’t get downloaded to the old location.

You can install a browser adblock plugin or addon for google chrome, firefox or safari, but but you will have to do this on each device. The network-wide ad-blocker is my favorite solution.

After clonning the git repository, do the local repository configuration, particularly set user name and email address.

When the site is generated with hugo it’s time to deploy it to some hosting platform. Here is a howto push it to AWS S3 and serve with AWS CloudFront CDN.

Comparing prediction speed of several versions of LLMs: llama3 (Meta/Facebook), phi3 (Microsoft), gemma (Google), mistral(open source) on CPU and GPU.

Here I am comparing several LLM versions: Llama3 (Meta), Phi3 (Microsoft), Gemma (Google), Mistral Nemo(Mistral AI) and Qwen(Alibaba).

Need to backup the 1) db, 2) filestorage, 3) some other gitea files. Here we go.