MAMuhammad Ariel Shakaramiroinshaka-ai.hashnode.dev·1d ago · 7 min readTransformer & Self-Attention: I Built an Encoder From Scratch, Then Caught It OverfittingThis week's topic is one of the most important building blocks of modern NLP: the Transformer and the self-attention mechanism behind it. Instead of just walking through the theory, I decided to build00
MAMuhammad Ariel Shakaramiroinshaka-ai.hashnode.dev·2d ago · 10 min readBuilding a Spam Classifier by Fine-tuning BERTA message like "Congratulations! You've won $10,000, click here to claim" reads as spam to pretty much anyone who gets it. What's worth digging into: a computer only sees a string of characters, so wh00
RSRahul Sai Indeevar Vinrahul-ai.hashnode.dev·Sep 5 · 9 min readLLM Architectures: From BERT and GPT-2 to XLNet and T5Understanding the internal mechanics of Large Language Model (LLM) architectures is crucial for building, fine-tuning, or deploying modern AI models. Why does GPT excel at text generation, while BERT 10
AAKSHAYinakshayetukurihashnodedev.hashnode.dev·Jul 4 · 4 min readFine-Tuning BERT to Classify Security Logs — And the 100% Accuracy Trap I Fell IntoThe idea Security teams deal with a constant stream of raw log lines — logins, file access, network connections, the occasional actual attack. Most of that triage still runs on hand-written regex rule00
RTRetzam Tarleinretzam.hashnode.dev·Mar 30 · 6 min readBERT, Dense Passage Retrieval, and how RAG was inventedHello 👽, Welcome to another mid-series special 🎉. I know I said we're done with BERT, but this is truly insightful 🤗, enjoy. While pretraining and fine-tuning the BERT (Bidirectional Encoder Repres00
RTRetzam Tarleinretzam.hashnode.dev·Feb 23 · 8 min readBERT in its ElementsHello 👽, I know, still on BERT, right? 😀. Well, it’s a lot to learn, and it’s worth it, no shortcuts 🦾. We learned about General Language Pre-training and a little about the architecture of BERT. W00
ASAlexey Sokolovinalexey-sokolov.hashnode.dev·Feb 9 · 9 min readI Bought an RTX 5070 Ti Because My 1-Year-Old Asked Me ToMy daughter recently told me she wanted a gaming PC with an RTX 5070 Ti. She's one year old and doesn't actually speak yet, but I'm pretty sure that's what the crying meant. So I did what any responsible parent would do — I bought one. Then I stared ...00
RTRetzam Tarleinretzam.hashnode.dev·Jan 26 · 4 min readIntroduction to BERT (Bidirectional Encoder Representations from Transformers)Aloha 👽, We learned a little about Large Language Models in our last series chapter, which brought us to the 3 types of LLMs (BERT, GPT, LLaMA). We’ll start with BERT. Let’s get right into it 🤖 It all started with Google Engineers yet again. Jacob ...00
SFShadab Firozintransformertextmodels.hashnode.dev·Jan 26 · 4 min readHow Transformer Text Models Are Revolutionizing NLP TechnologyComparison of Transformer Variants for Text Classification Text classification is one of the most widely used tasks in natural language processing (NLP), powering applications such as sentiment analysis, spam detection, topic labeling, intent reco...00
NMNastaran Moghadasiinnastaran.hashnode.dev·Dec 22, 2025 · 5 min readHow AI Knows a Cat Is Like a Dog: An Intuitive Guide to Word EmbeddingsHave you ever wondered how a computer knows that a cat is more like a dog than a car? To a machine, words are just strings of characters or arbitrary ID numbers. But in the world of Natural Language Processing, we’ve found a way to give words a home ...00
