Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Announcing Eric Siegel’s New Book: The AI Playbook
  Dear Reader, I’m excited to announce the forthcoming,...
Predictive Analytics for the Call Center
 So, you just received your shiny new smart watch....
MLW Preview Video: Gulrez Khan, Data Science Lead at PayPal
 In anticipation of his upcoming keynote presentation at Predictive...
MLW Preview Video: Devanshi Vyas, Co-Founder at Censius
 In anticipation of her upcoming presentation at Deep Learning...

LLM

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

 Originally published in together.ai, Sept 11, 2023. Large Language Models (LLMs) have changed the world. However, generating text with them can be slow and expensive. While methods like speculative decoding have been proposed to accelerate the generation speed, their intricate nature has left many in the open-source community hesitant to embrace them. That’s why we’re

Can LLMs Learn From a Single Example?

 Originally published in Fast.AI, Sept 4, 2023. We’ve noticed an unusual training pattern in fine-tuning LLMs. At first we thought it’s a bug, but now we think it shows LLMs can learn effectively from a single example....

Meta Launches Own AI Code-Writing Tool: Code Llama

 Originally posted in The Verge, Aug 24, 2023. Meta said Code Llama will make it easier to finish code. Meta has released a tool called Code Llama, built on top of its Llama 2 large language model, to generate...

Productizing Large Language Models

 Originally posted on Replit.com, Sept 21, 2022.  Large Language Models (LLMs) are known for their near-magical ability to learn from very few examples — as little as zero — to create language wonders. LLMs can chat, write...