How to Find an Apartment in Munich — My Experience and TipsFinding an apartment in Munich is notoriously difficult. If you’re reading this, chances are you’ve already heard about how competitive…Mar 26Mar 26
Published inDev GeniusHow to Run a LLM Locally with Ollama and Open WebUILarge Language Models (LLMs) have changed the way we interact with AI. While cloud-based services are convenient, running a LLM locally…Mar 23Mar 23
Published inDev GeniusConda vs Virtual Environments: Which One Should You Choose for Your Python Projects?In the world of Python development, managing dependencies and maintaining separate environments is critical for ensuring smooth project…Dec 30, 2024Dec 30, 2024
Comparing Two Methods for Photon Energy Calibration in Free-Electron Lasers (FELs)Accurately calibrating photon energy is a critical task in X-ray Free-Electron Lasers (XFELs), especially for ensuring the precision of…Dec 29, 2024Dec 29, 2024
Published inDev GeniusWriting ETL Pipelines in Python: A Step-by-Step GuideIn the realm of data engineering and analysis, Extract, Transform, Load (ETL) pipelines serve as the backbone for processing and…Apr 13, 2024Apr 13, 2024
Fine-Tuning Your Own Custom PyTorch ModelFine-tuning a pre-trained PyTorch model is a common practice in deep learning, allowing you to adapt an existing model to a new task with…Mar 15, 2024Mar 15, 2024
Published inDev GeniusUnlock Faster LLM Serving with vLLM: A Step-by-Step GuideIn this article we will compare running four prompts with Mistral-7B with and without vLLM, and compare the duration in both cases.Feb 25, 2024Feb 25, 2024
Building a Retrieval Augmented Generation Model Using Hugging Face Zephyr LLM and LangChainNot a member? Click hereFeb 19, 20241Feb 19, 20241
Evaluating RAG Performance: A Comprehensive GuideRetrieval Augmented Generation (RAG) systems are intricate, with various components influencing their performance. Implementing…Feb 16, 20244Feb 16, 20244