- 
Pretraining: Breaking Down the Modern LLM Training PipelineLLM training shapes everything from what a model knows to how it reasons and responds. So, understanding how models are… 
- 
LLM Juries for EvaluationEvaluating the correctness of generated responses is an inherently challenging task. LLM-as-a-Judge evaluators have gained popularity for their ability to… 
- 
G-Eval for LLM EvaluationLLM-as-a-judge evaluators have gained widespread adoption due to their flexibility, scalability, and close alignment with human judgment. They excel at… 
- 
Building ClaireBot, an AI Personal Stylist ChatbotFollow the evolution of my personal AI project and discover how to integrate image analysis, LLM models, and LLM-as-a-judge evaluation… 
- 
Perplexity for LLM EvaluationPerplexity is, historically speaking, one of the “standard” evaluation metrics for language models. And while recent years have seen a… 
- 
Building a Low-Cost Local LLM Server to Run 70 Billion Parameter ModelsA guest post from Fabrício Ceolin, DevOps Engineer at Comet. Inspired by the growing demand for large-scale language models, Fabrício… 
- 
Turning Raw Data Into Fine-Tuning DatasetsWelcome to Lesson 6 of 12 in our free course series, LLM Twin: Building Your Production-Ready AI Replica. You’ll learn how to use… 
- 
The 4 Advanced RAG Algorithms You Must Know to ImplementWelcome to Lesson 5 of 12 in our free course series, LLM Twin: Building Your Production-Ready AI Replica. You’ll learn how to use LLMs,… 
- 
SOTA Python Streaming Pipelines for Fine-tuning LLMs and RAG – in Real-Time!Welcome to Lesson 4 of 12 in our free course series, LLM Twin: Building Your Production-Ready AI Replica. You’ll learn… 
- 
I Replaced 1000 Lines of Polling Code with 50 Lines of CDC MagicWelcome to Lesson 3 of 12 in our free course series, LLM Twin: Building Your Production-Ready AI Replica. You’ll learn… 













