Friday, 10 Apr 2026
Subscribe
logo
  • Global
  • AI
  • Cloud Computing
  • Edge Computing
  • Security
  • Investment
  • Sustainability
  • More
    • Colocation
    • Quantum Computing
    • Regulation & Policy
    • Infrastructure
    • Power & Cooling
    • Design
    • Innovations
    • Blog
Font ResizerAa
Data Center NewsData Center News
Search
  • Global
  • AI
  • Cloud Computing
  • Edge Computing
  • Security
  • Investment
  • Sustainability
  • More
    • Colocation
    • Quantum Computing
    • Regulation & Policy
    • Infrastructure
    • Power & Cooling
    • Design
    • Innovations
    • Blog
Have an existing account? Sign In
Follow US
© 2022 Foxiz News Network. Ruby Design Company. All Rights Reserved.
Data Center News > Blog > AI > Stability AI unveils 12B parameter Stable LM 2 model and updated 1.6B variant
AI

Stability AI unveils 12B parameter Stable LM 2 model and updated 1.6B variant

Last updated: April 9, 2024 9:28 pm
Published April 9, 2024
Share
Stability AI unveils 12B parameter Stable LM 2 model and updated 1.6B variant
SHARE

Stability AI has introduced the most recent additions to its Secure LM 2 language mannequin sequence: a 12 billion parameter base mannequin and an instruction-tuned variant. These fashions had been educated on a powerful two trillion tokens throughout seven languages: English, Spanish, German, Italian, French, Portuguese, and Dutch.

The 12 billion parameter mannequin goals to strike a steadiness between robust efficiency, effectivity, reminiscence necessities, and pace. It follows the established framework of Stability AI’s beforehand launched Secure LM 2 1.6B technical report. This new launch extends the corporate’s mannequin vary, providing builders a clear and highly effective software for innovating with AI language know-how.

Alongside the 12B mannequin, Stability AI has additionally launched a brand new model of its Secure LM 2 1.6B mannequin. This up to date 1.6B variant improves dialog talents throughout the identical seven languages whereas sustaining remarkably low system necessities.

Secure LM 2 12B is designed as an environment friendly open mannequin tailor-made for multilingual duties with clean efficiency on broadly accessible {hardware}.

Based on Stability AI, this mannequin can deal with duties sometimes possible just for considerably bigger fashions, which frequently require substantial computational and reminiscence assets, corresponding to giant Combination-of-Specialists (MoEs). The instruction-tuned model is especially well-suited for numerous makes use of, together with as a central a part of retrieval RAG methods, resulting from its excessive efficiency in software utilization and performance calling.

In efficiency comparisons with in style robust language fashions like Mixtral, Llama2, Qwen 1.5, Gemma, and Mistral, Secure LM 2 12B affords strong outcomes when examined on zero-shot and few-shot duties throughout normal benchmarks outlined within the Open LLM leaderboard:

See also  HUGO Meme Coin Unveils AI-Driven Transparency Tool as Multi-Chain Expansion Begins

With this new launch, Stability AI extends the StableLM 2 household into the 12B class, offering an open and clear mannequin with out compromising energy and accuracy. The corporate is assured that this launch will allow builders and companies to proceed creating the longer term whereas retaining full management over their information.

Builders and companies can use Secure LM 2 12B now for business and non-commercial functions with a Stability AI Membership.

(Picture by Muha Ajjan)

See additionally: ML Olympiad returns with over 20 challenges

Wish to be taught extra about AI and large information from trade leaders? Take a look at AI & Big Data Expo happening in Amsterdam, California, and London. The great occasion is co-located with different main occasions together with BlockX, Digital Transformation Week, and Cyber Security & Cloud Expo.

Discover different upcoming enterprise know-how occasions and webinars powered by TechForge here.

Tags: ai, synthetic intelligence, improvement, language fashions, stability ai, secure lm 2

Source link

TAGGED: 1.6B, 12B, Model, parameter, Stability, Stable, unveils, Updated, variant
Share This Article
Twitter Email Copy Link Print
Previous Article reshape Reshape Raises $20M in Series A Funding
Next Article dcw 2023 registration desk from above Data Center World 2024: The Sessions I Don’t Want to Miss | DCN
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Your Trusted Source for Accurate and Timely Updates!

Our commitment to accuracy, impartiality, and delivering breaking news as it happens has earned us the trust of a vast audience. Stay ahead with real-time updates on the latest events, trends.
FacebookLike
TwitterFollow
InstagramFollow
YoutubeSubscribe
LinkedInFollow
MediumFollow
- Advertisement -
Ad image

Popular Posts

AI commentary goes into full swing at Players Championship

Inbuilt partnership with Amazon Internet Companies (AWS), AI commentary runs on Amazon Bedrock and makes…

April 7, 2025

Salute gears up for the AI era with ADCC Group acquisition

Salute has introduced the acquisition of Superior Knowledge Heart Consulting Group (ADCC Group), as a…

March 30, 2025

Macquarie Data Centres, Dell Technologies Partner to Deliver Sovereign AI Factories in Australia

Picture: Macquarie Knowledge Centres x Dell Applied sciences staff L to R: Paul Christensen GM…

August 12, 2025

Data centres driving AI and sustainability

Charlie Hesketh, Technique and Funding Director at Aurora Utilities Restricted, explores the altering form of…

December 17, 2024

OpenAI Announces Stargate Data Center Expansion in Abu Dhabi

(Bloomberg) -- OpenAI helps to develop a significant information heart within the United Arab Emirates,…

May 22, 2025

You Might Also Like

Why companies like Apple are building AI agents with limits
AI

Why companies like Apple are building AI agents with limits

By saad
Agentic AI's governance challenges under the EU AI Act in 2026
AI

Agentic AI’s governance challenges under the EU AI Act in 2026

By saad
Anthropic keeps new AI model private after it finds thousands of external vulnerabilities
AI

Anthropic keeps new AI model private after it finds thousands of external vulnerabilities

By saad
Microsoft open-source toolkit secures AI agents at runtime
AI

Microsoft open-source toolkit secures AI agents at runtime

By saad
Data Center News
Facebook Twitter Youtube Instagram Linkedin

About US

Data Center News: Stay informed on the pulse of data centers. Latest updates, tech trends, and industry insights—all in one place. Elevate your data infrastructure knowledge.

Top Categories
  • Global Market
  • Infrastructure
  • Innovations
  • Investments
Usefull Links
  • Home
  • Contact
  • Privacy Policy
  • Terms & Conditions

© 2024 – datacenternews.tech – All rights reserved

Welcome Back!

Sign in to your account

Lost your password?
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.
You can revoke your consent any time using the Revoke consent button.