Big Data News Hubb
Advertisement
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
Big Data News Hubb
No Result
View All Result
Home Big Data

Research Highlights: SparseGPT: Prune LLMs Accurately in One-Shot

admin by admin
March 3, 2023
in Big Data


Achieve 50% Sparsity With One-Shot Learning Without Any Retraining

It might come as a surprise, but large language models are a great match for sparsification. Why? They give up less accuracy as compared to the amount of weights that are being eliminated (set to 0). This is an encouraging finding from Neural Magic‘s collaboration with the Institute of Science and Technology Austria (ISTA) because it makes it possible to run billion parameter models more efficiently, with significantly less hardware.

A new research paper shows that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models. When executing SparseGPT on the largest available open-source models, OPT-175B and BLOOM-176B, we can reach 60% sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these models can be ignored at inference time. SparseGPT generalizes to semi-structured (2:4 and 4:8) patterns, and is compatible with weight quantization approaches.

Sign up for the free insideBIGDATA newsletter.

Join us on Twitter: https://twitter.com/InsideBigData1

Join us on LinkedIn: https://www.linkedin.com/company/insidebigdata/

Join us on Facebook: https://www.facebook.com/insideBIGDATANOW





Source link

Previous Post

Implementing Disaster Recovery for a Databricks Workspace

Next Post

Why I Prefer Cloudera CDP

Next Post

Why I Prefer Cloudera CDP

Recommended

How To Increase Your Company’s Capabilities

October 13, 2022

Improve observability across Amazon MWAA tasks

February 12, 2023

Isolated environments for Distributed governance with Unity Catalog

March 10, 2023

Don't miss it

News

How Enterprises Can Defray the Hidden Cost of the Cloud

March 23, 2023
Big Data

Evolution through large models

March 23, 2023
Big Data

Observe Everything – Cloudera Blog

March 22, 2023
Big Data

NVIDIA Launches Inference Platforms for Large Language Models and Generative AI Workloads

March 22, 2023
Big Data

Announcing the General Availability of Private Link and CMK for Databricks on AWS

March 22, 2023
News

Manage users and group memberships on Amazon QuickSight using SCIM events generated in IAM Identity Center with Azure AD

March 22, 2023

big-data-footer-white

© 2022 Big Data News Hubb All rights reserved.

Use of these names, logos, and brands does not imply endorsement unless specified. By using this site, you agree to the Privacy Policy and Terms & Conditions.

Navigate Site

  • Home
  • Big Data
  • News
  • Contact us

Newsletter Sign Up

No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us

© 2022 Big Data News Hubb All rights reserved.