All articles

Fine-tuning allows to adapt generalist models into specialists, but is it always the best approach?

Quantization is a model compression technique that reduces the size and computational requirements of LLMs.

A practical guide to finally understanding most popular LLM benchmarks

What is the difference between base and instruction-tuned models?

Parameter is a key concept in LLMs. This article explains the difference between total and activated parameters.

What are AI agents, how they work, and how they differ from LLMs and workflows?

Two quite old, but very powerful concepts that are the foundation of modern AI applications.

Unlocking AI's potential with the Model Context Protocol (MCP).

A (not only) software developer's guide to Large Language Models (LLMs).

An overview of Hugging Face 🤗, its ecosystem (libraries, tools, etc.), and how to leverage it for AI development.

Distillation is a technique for creating smaller, faster, and more efficient AI models that inherit the wisdom of their larger counterparts. Why and how to use it?

AI and LLMs are changing the way we interact with the web. The llms.txt file is a new proposed standard that helps LLMs understand website content more effectively.

AI is everywhere. As majority of companies already is using (and paying for) GitHub, it is worth to know what AI tools GitHub offers to developers.