top of page

Salesforce AI Introduces CodeT5+: A New Family of Open Code Large Language Models

  • Writer: Joseph K
    Joseph K
  • May 19, 2023
  • 1 min read

Modern large language models (LLMs) have excellent performance on code reading and generation tasks, allowing more people to enter the once-mysterious field of computer programming. Architecturally, existing code LLMs use encoder- or decoder-only models, which excel at just some comprehension and generating tasks. Code-focused LLMs typically have a limited set of pretraining objectives, which will degrade performance on downstream tasks that are less relevant to those objectives, and they often adopt an encoder-only or decoder-only architecture, which can limit their optimal performance to only specific tasks.





 
 
 

Comments


Recent Posts

Get In Touch

Want to learn more about our past work or

explore how we can support your current initiatives?

Reach out today and let Fiduciary Tech be your trusted partner.

Headquarters

1100 106th Avenue NE, Suite 101F
Bellevue, WA 98004
425-998-8505

info@fiduciarytech.com

Seoul Office

Address: Geunshin Building 506-1, 20 Samgae-ro, Mapo-gu, Seoul, 04173, Republic of Korea
02-71
2-2227

info@fiduciarytech.com

fiduciary technology consulting

© 2025 by Fiduciary Technology Solutions 

bottom of page