Published in

Scaling large language models

The new breed of NLP models outperform the GPT-3. Think the PaLM model as one approach.

Photo by Ryunosuke Kikuno on Unsplash


The OpenAI released the GPT-3 in June 2020. Now, after two years — we see competitors emerging.

Several of them use novel approaches to achieve State-of-the-Art performance compared against the GPT-3.




Data Scientists must think like an artist when finding a solution when creating a piece of code. ⚪️ Artists enjoy working on interesting problems, even if there is no obvious answer ⚪️ 🔵 Follow to join our 18K+ Unique DAILY Readers 🟠

Recommended from Medium

All is well that ends well with Generative Adversarial Networks!

I did something boring so you don’t have to

Understanding Skip Connections in Convolutional Neural Networks using U-Net Architecture

Gradient Boosting Machines (GBMs)— the ELI5 way

How You are Already Using NLP Daily

NLP Everyday (Source:

Understanding Word Embeddings

Data Leakage during ML Modelling

Reducing latency in tensorflow lite

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Teemu Maatta

Teemu Maatta

Machine Learning Engineer. Top writer in Natural Language Processing (NLP). Multimodal learning. Artificial General Intelligence (AGI). DALL·E 2. GPT-3.

More from Medium

GPT-J vs GPT-3 in

Meta-Learning the Huggingface Way

Generative Pre-trained Transformer 3 by OpenAI

Meta AI Open-Sources a 175B Parameter Language Model: GPT-3 Comparable Performance at One-Seventh…