Comparing LLM Summarising Abilities
8 llama3 (Meta+) and 5 phi3 (Microsoft) LLM versions
Testing how models with different number of parameters and quantization are behaving.
8 llama3 (Meta+) and 5 phi3 (Microsoft) LLM versions
Testing how models with different number of parameters and quantization are behaving.
Ollama LLM model files take a lot of space
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.
It's so annoying to watch all those ads
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.
Let's test logical fallacy detection quality of different LLMs
Here I am comparing several LLM versions: Llama3 (Meta), Phi3 (Microsoft), Gemma (Google), Mistral Nemo(Mistral AI) and Qwen(Alibaba).
Anything can happen in these difficult times
Need to backup the 1) db, 2) filestorage, 3) some other gitea files. Here we go.
To use container registry in k8s we need it over ssl
We want to host a nice and secure container registry - to push docker images there and our kubernetes cluster would pull them from this registry. So came the idea to use the gitea over ssl.
Trying to choose good opensource git server
Wanting to move your projects away from open cloud git providers and thinking of self-hosting internal git server locally?
Useful Hugo commands params
Hugo is a static website generator. It helps produce html from markup, theme and keep website organised. Like this tech blog. Here’s a list of the most useful Hugo commands with their parameters:
cUrl useful commands with params
Here’s a cheatsheet for the most useful cURL commands with their parameters: