← News
News & insights
Tutorials
How language models work, explained without jargon: inference, training, fine-tuning, the layers inside.
Guides
How a model writes its answerHow a model is trainedHow we fine-tune a modelThe layers we put on a modelGlossary
The first articles of this section are in review.
Library
Short practical articles on language models from the xbe.at knowledge base.
LLMs and generative AI
Large language models, retrieval, agents, fine-tuning and prompting.
Agents and LangChain
Integrating YOLO OCR and AI Agents for Document Organization29 min read · xbe.at ↗Building LLMs from Scratch Python Practical Code Examples15 min read · xbe.at ↗Building and Deploying an LLM Agent in Python A Step-by-Step Guide15 min read · xbe.at ↗Swarm OpenAI's Multi-Agent Orchestration Framework12 min read · xbe.at ↗Building an Agentic Mesh for Autonomous Agents12 min read · xbe.at ↗Bridging LLMs and Graph Learning with Python11 min read · xbe.at ↗
All 32 on xbe.at ↗
Fine tuning and alignment
Fundamental Topics of LLM Fine-tuning16 min read · xbe.at ↗Efficient LLM Fine-Tuning with LoRA15 min read · xbe.at ↗Techniques for Fine-Tuning Large Language Models12 min read · xbe.at ↗Entropic Distribution Matching for Supervised LLM Fine-tuning12 min read · xbe.at ↗Knowledge Distillation in Large Language Models12 min read · xbe.at ↗Mastering AI with Fine-Tuning Large Language Models12 min read · xbe.at ↗
All 25 on xbe.at ↗
LLM architecture and theory
Addressing Hallucinations in Large Language Models15 min read · xbe.at ↗Positional Encodings in Transformer LLMs14 min read · xbe.at ↗Transformer Architecture for Efficient LLM Processing13 min read · xbe.at ↗Comparing Dense, Sparse, and Mixture of Experts for LLMs12 min read · xbe.at ↗Evaluating Large Language Models 30 Common Metrics12 min read · xbe.at ↗The Exponential Growth of Large Language Models11 min read · xbe.at ↗
All 45 on xbe.at ↗
RAG and retrieval
Chunking Strategies for Improved RAG Performance19 min read · xbe.at ↗Retrieval-Augmented Generation (RAG) vs. HyDE Revolutionizing Text Generation18 min read · xbe.at ↗Retrieval Augmented Generation (RAG) in Large Language Models16 min read · xbe.at ↗Addressing LLM Limitations with RAG Document Q&A15 min read · xbe.at ↗Low-Latency Boost for Context in RAG Pipelines Rerankers14 min read · xbe.at ↗Comparing RAG and Fine-Tuned Language Models14 min read · xbe.at ↗
All 39 on xbe.at ↗
Vector databases and embeddings
Understanding Vector Databases Fundamentals and Applications14 min read · xbe.at ↗Introduction to LLM-based Text-to-SQL Integration12 min read · xbe.at ↗MatMul-Free LLMs for Enhanced Efficiency in Python11 min read · xbe.at ↗Embeddings Re-ranking and Vector Databases in Python11 min read · xbe.at ↗Decoding Embedding in LLMs with Python10 min read · xbe.at ↗Choosing the Best Embedding Model for RAG in Python10 min read · xbe.at ↗
All 22 on xbe.at ↗
NLP and transformers
Text processing, embeddings, attention and transformer models.
BERT and language models
Exploring Vector Embeddings in Language Models14 min read · xbe.at ↗Essential Language Model Terms for Everyday Use12 min read · xbe.at ↗Quantization Effects on Multilingual Language Models11 min read · xbe.at ↗Understanding BERT A Cornerstone of NLP with Python11 min read · xbe.at ↗Understanding Embeddings and Sentence Transformers in NLP11 min read · xbe.at ↗Contextual Awareness in AI and Language Models11 min read · xbe.at ↗
All 32 on xbe.at ↗
NLP core
The Importance of Tokenization in NLP17 min read · xbe.at ↗Sentiment Analysis Techniques in Python13 min read · xbe.at ↗Comparing Transformer Models for Sentiment Analysis13 min read · xbe.at ↗Named Entity Recognition with Python12 min read · xbe.at ↗Understanding Word Embeddings in Machine Learning12 min read · xbe.at ↗Machine Learning Models for Sentiment Analysis in Python12 min read · xbe.at ↗
All 36 on xbe.at ↗
Transformer architecture
Attention Mechanism in Deep Learning17 min read · xbe.at ↗Attention Mechanism in Language Models16 min read · xbe.at ↗Transformers Revolutionizing Natural Language Processing16 min read · xbe.at ↗Dualformer Combining Fast and Slow Reasoning in Transformers15 min read · xbe.at ↗Positional Encoding in Transformer Models14 min read · xbe.at ↗Positional Encoding in Transformer Architectures13 min read · xbe.at ↗
All 48 on xbe.at ↗