Tag

#transformers

535 posts46 followers

Explore Hashnode

Alternatives

Nishanthan Karunakaran15h ago · 7 min read

How Query, Key, and Value (QKV) Work in Transformers

Every Transformer-based language model, from BERT to GPT, relies on a mechanism called attention to determine how different tokens in a sequence relate to one another. At the heart of this mechanism a

nishanthan.hashnode.dev

Sai Sandeep Kantareddy2d ago · 9 min read

Routing AI Requests Without Training Data and Knowing When to Train a Classifier

The retail examples below are illustrative; they do not report measured production results or disclose an employer's implementation. A team adds three specialist agents to an assistant. Routing looks

3 tokenbytoken.hashnode.dev

Nishanthan KarunakaranOct 15 · 6 min read

Understanding Transformer: The Architecture Behind Modern AI

What Is a Transformer? A Transformer is a neural network architecture introduced by Google researchers in 2017 in the paper Attention Is All You Need. It uses attention mechanisms to help the model le

nishanthan.hashnode.dev

Mahesh MoholkarOct 13 · 43 min read

Building a Modern LLM from Scratch: RMSNorm, RoPE, GQA and SwiGLU

This is the fourth part of a series on how language models work, built from the ground up. Part 1 built a neural network as an office building and trained it. Part 2 put text through the building and

maheshmoholkar.hashnode.dev

ZyVOPOct 3 · 26 min read

Build a Small LLM From Scratch: A Tested GPT in PyTorch

You can train a real language model on a laptop CPU during a coffee break. It won't be smart. It will have every part a big one has. This post builds one. It's a decoder-only transformer in PyTorch, t

blog.zyvop.com

Surendranath Reddy JillellaSep 24 · 9 min read

We Tested TypeSafe AI's Jev on Screen Classification: 20x Faster, 153x Cheaper, and Noticeably Less Accurate

TypeSafe AI's Jev promises a faster, cheaper alternative to LLMs for structured decisions, so we put it to work on a real production task at QApilot: classifying screens for our autonomous mobile app

2 qapilot-ai.hashnode.dev

Ekansh NangiaSep 17 · 18 min read

Introduction To Mechanistic Interpretability

Epistemology Epistemology is the branch of philosophy thats concerned with the nature and limits of knowledge. What knowledge actually is, how we get it, and how we tell the difference between somethi

ekanshn.hashnode.dev

Lakshya PadhanSep 15 · 14 min read

Attention Is All You Need: The Paper That Changed Modern AI

An accessible deep dive into the 2017 research paper that introduced the Transformer architecture In 2017, a research paper with a surprisingly confident title — “Attention Is All You Need” — introduc

theainotebooklakshya.hashnode.dev

Tech-AarvamSep 15 · 14 min read

Puzzle Solution Revealed - Transformer: Need for Position Embedding

Introduce position embedding, residuals and layers ▶ Watch the 7-minute walkthrough import torch torch.set_printoptions(precision=2, sci_mode=False, linewidth=160) In this notebook we are extending

techaarvam.hashnode.dev

Mahesh MoholkarSep 12 · 70 min read

Text to Attention From Scratch

This is the second part of a series on how language models work, built from the ground up. The first part covered what a neural network is made of and how it learns: an office building of workers, man

maheshmoholkar.hashnode.dev

Search Hashnode

Explore Hashnode

Trending tags this week

How Query, Key, and Value (QKV) Work in Transformers

Routing AI Requests Without Training Data and Knowing When to Train a Classifier

Understanding Transformer: The Architecture Behind Modern AI

Building a Modern LLM from Scratch: RMSNorm, RoPE, GQA and SwiGLU

Build a Small LLM From Scratch: A Tested GPT in PyTorch

We Tested TypeSafe AI's Jev on Screen Classification: 20x Faster, 153x Cheaper, and Noticeably Less Accurate

Introduction To Mechanistic Interpretability

Attention Is All You Need: The Paper That Changed Modern AI

Puzzle Solution Revealed - Transformer: Need for Position Embedding

Text to Attention From Scratch