Tag feed

#gpt

285 posts69 followers

Explore Hashnode

Alternatives

Trending tags this week

DDimondimonb19a.hashnode.devJul 18 · 7 min read

GPT Is a Nerd, Claude Is a Colleague: Why AI Models Have Personalities (and Why It Matters)

Where this started I'm a frontend engineer, and at this point almost none of my code is written by hand. I manage an AI, review its implementation, tweak the occasional style rule. Somewhere along the

0

DNDebashis Nandydebashisn.hashnode.devJul 18 · 8 min read

RAG: The Ground-Up Guide

What is RAG? 💡 Please make sure you have the basic understanding of LLM. In today's AI landscape, powerful Large Language Models (LLMs) from industry giants like OpenAI, Anthropic, xAI, and Google

0

AJAman Jaincurious-pm.hashnode.devJul 17 · 11 min read

Learning Rate Is More Than Just a Number

In the previous article, I tested a reusable experimentation framework with a small learning-rate sweep. Within the range I tried, higher learning rates produced lower validation loss—but the best res

0

AJAman Jaincurious-pm.hashnode.devJul 17 · 8 min read

From Building a GPT Model to Experimenting With One

Over the last few articles, I built the transformer block, assembled the complete GPT architecture, loaded pretrained GPT-2 weights, fine-tuned the model for classification and instruction tasks, and

0

AJAman Jaincurious-pm.hashnode.devJul 16 · 10 min read

Building a GPT Model from Scratch (Part 5): Fine-Tuning GPT-2 for Text Classification

In the previous article, we loaded OpenAI’s pretrained GPT-2 weights into the model we had built from scratch. Now, we will adapt that model for text classification—specifically, identifying whether a

0

AJAman Jaincurious-pm.hashnode.devJul 16 · 13 min read

Building a GPT Model from Scratch (Part 4): Training and Loading Pretrained Weights

In the previous article, we completed the base architecture of our GPT model. The token and positional embeddings, transformer blocks, normalization layers, and output layer were all in place. The mod

0

AJAman Jaincurious-pm.hashnode.devJul 14 · 8 min read

LLM architecture (part 2): Inside a Transformer Block

In the previous article, we looked at tokenization and embeddings, which convert a finite vocabulary into continuous vectors that we can work with mathematically. We also explored attention, which hel

0

AJAman Jaincurious-pm.hashnode.devJul 14 · 9 min read

LLM architecture (part 3): Assembling model

At this point, we have almost everything we need to assemble a baseline GPT model. In this article, I will: Bring the different components together and show how they form the complete model. Do a qu

0

AJAman Jaincurious-pm.hashnode.devJul 11 · 7 min read

Why I Built a GPT Model From Scratch — and What I Actually Built

“To exist is to change, to change is to mature, to mature is to go on creating oneself endlessly.” - Henri Bergson Let me start by saying a little bit about myself, just to put this whole exercise in

0

BBrijenderbrijender.hashnode.devJul 1 · 16 min read

GPT & LLM Explained: How Text Becomes Intelligence

A few years ago, talking to computers felt mechanical. We had to click menus, fill forms, use exact keywords, or write code. Now we type: “Explain transformers like I am a software engineer moving in

0

#gpt

Search Hashnode

#gpt

Explore Hashnode

Trending tags this week

GPT Is a Nerd, Claude Is a Colleague: Why AI Models Have Personalities (and Why It Matters)

RAG: The Ground-Up Guide

Learning Rate Is More Than Just a Number

From Building a GPT Model to Experimenting With One

Building a GPT Model from Scratch (Part 5): Fine-Tuning GPT-2 for Text Classification

Building a GPT Model from Scratch (Part 4): Training and Loading Pretrained Weights

LLM architecture (part 2): Inside a Transformer Block

LLM architecture (part 3): Assembling model

Why I Built a GPT Model From Scratch — and What I Actually Built

GPT & LLM Explained: How Text Becomes Intelligence