The Raise of AI Agents
The landscape of artificial intelligence is rapidly evolving, and one of the most exciting developments is the emergence of AI agents. As we approach a new era where 2025 is being hailed as the y...
Gian Paolo Santopaolo
RAG vs. CAG: A New Frontier in Augmenting Language Models
Large language models (LLMs) are undoubtedly powerful—but they come with a catch: a knowledge cutoff. If a fact wasn’t in the training data or if it’s something new (like who won the 2025 Best Pic...
How TRLParser Is Revolutionizing Our Fine-Tuning Workflow
Fine-tuning large language models can quickly become a tangled mess of code and configuration, especially when we’re experimenting with different strategies. Recently, I rewrote Teaching an LLM H...
Understanding Key Hyperparameters When Fine-Tuning an LLM
Fine-tuning a large language model depends on optimizing several key hyperparameters to unlock its full potential. In this discussion, we focus on the three most important hyperparameters – batch s...
TrlParser simplifies our fine-tune code
In the ever-changing world of machine learning, keeping our code simple and easy to maintain is more important than ever. That’s where TrlParser comes in—a smart extension of Hugging Face’s HfArgu...
Everything You Need to Know About Fine-Tuning LLMs
Let’s recap how LLMs are created, it will help to better understand the whole fine-tuning pipeline. The training lifecycle typically involves three stages: Pre-training The model is initially...
Adding TensorBoard to Your Keras Workflow
Adding TensorBoard as a data visualization tool to your Keras model is easier than you might think. With just a few extra lines of code, you can gain valuable insights into your model’s training pr...
Data Visualization with Weights & Biases: A Powerful Tool for Tracking and Organizing ML Experiments
Weights & Biases (W&B) is not just a logging tool—it’s a robust platform that makes your machine learning experiments organized, reproducible, and visually compelling. In this article, we d...
Forecasting Your Private LLM Resources: Unlocking Lightning-Fast, Scalable AI Performance
Keeping your data in-house In today’s data-driven world, companies are increasingly concerned about sensitive data leaving their boundaries. Deploying your own Large Language Model (LLM) isn’t jus...
Surgical Fine-Tuning: Precision Adjustments for Language Models with PyReFT
Surgical Fine-Tuning: Precision Adjustments for Language Models with PyReFT Fine-tuning large language models (LMs) can be a challenging task, especially when trying to achieve high performance wi...