Ignasi Lopez Luna
-
LoRA Explained: Faster, More Efficient Fine-Tuning with Docker
LoRA is a method that freezes a base model and adds trainable adapters to teach pre-trained models new behaviors, without overwriting their existing knowledge.
Ignasi Lopez LunaRead now
-
Fine-Tuning Local Models with Docker Offload and Unsloth
Learn how to fine-tune models locally with Docker Offload and Unsloth and how smaller models can become practical assistants for real-world problems.
Ignasi Lopez LunaRead now
-
Hybrid AI Isn’t the Future — It’s Here (and It Runs in Docker using the Minions protocol)
Learn how to use Docker Compose, Model Runner, and the MinionS protocol to deploy hybrid models.
Ignasi Lopez LunaRead now
-
Tool Calling with Local LLMs: A Practical Evaluation
Find the best local LLM for tool calling to use on your agentic applications with this carefully tested leaderboard from Docker.
Ignasi Lopez LunaRead now
-
Run Gemma 3 with Docker Model Runner: Fully Local GenAI Developer Experience
Explore how to run Gemma 3 models locally using Docker Model Runner, alongside a Comment Processing System as a practical case study.
Ignasi Lopez LunaandOmar SansevieroRead now
-
How to Run Hugging Face Models Programmatically Using Ollama and Testcontainers
Learn how you can programmatically consume and run AI models from Hugging Face with Testcontainers and Ollama.
Read now
-
A Promising Methodology for Testing GenAI Applications in Java
Testing applications that incorporate AI can be difficult. In this article, we share a promising new methodology for testing GenAI applications in Java.
Read now