🏴 Context Engineering in 2 Minutes
Understanding why context engineering is crucial for LLM agents - giving models only what they really need for better performance and lower costs.
Writing on tech exploration, learning advancements, and project insights.
Chronicling my journey through courses and projects to master emerging technologies, and sharing the knowledge gained along the way.
🏴 Boost Your RAG Pipeline Performance with Fine-Tuning Your Embedding Model
Learn how to fine-tune Hugging Face embedding models on your own data using contrastive learning with MultiNegativeRankingLoss.
🏴 Memory Requirements for Finetuning Large Language Models
Understanding the massive memory demands of finetuning 70B parameter models and efficient solutions like LoRA and QLoRA.
🏴 LLaMA2 PyTorch from Scratch (WiP)
This project aims to demystify the inner workings of modern Large Language Models (LLMs) by implementing Llama2 from scratch.
🇩🇪 HM-Studierender wird Fellow für ein Digitalprojekt im Bundesfinanzministerium
Arbeitsprozesse der Bundesverwaltung digitalisieren: dafür steht das seit fünf Jahren jährlich ausgelobte Tech4GermanyFellowship. Es verbindet die zwei Welten „Bürokratie“ und „Tech“. HM-Bachelorand Christian Bernhard war 2022 als Stipendiat dabei.