header lang header lang EN
sambanova-logo-black
Products
SambaNova’s AI platform is the technology backbone for the next decade of AI innovation. Customers are turning to SambaNova to quickly deploy state-of-the-art AI and deep learning capabilities that help them outcompete their peers.
SambaNova Suite
The only, enterprise grade full stack platform, purpose built for generative AI
DataScale®
The platform for generative AI development and innovation
Use Cases
Public Sector | AI for Science | Sovereign AI
Technology
RDU: The GPU Alternative
Power the most demanding generative and agentic AI workloads with the most performant & capable processor, purpose-built for AI
Composition of Experts
Easily run your custom models, accelerate discovery, & power the next generation of high performance computing
Developers
SambaNova delivers the only enterprise-grade full stack platform, from chips to models, purpose built for generative AI
SambaNova Cloud
Supercharge your AI-powered applications across Llama 3 8B, 70B, & 405B models.
For free.
SambaNova Startup Accelerator
Our program tailored to support early-stage startups in achieving breakthrough AI innovation.
Developer Resources
Developer Community
Starter Kits
Research
Technical Documentation
Resources
Find what you need to accelerate your AI journey.
About
Customers are turning to SambaNova to quickly deploy state-of-the-art AI capabilities to gain competitive advantage. Our purpose-built enterprise-scale AI platform is the technology backbone for the next generation of AI computing. We power the foundation models that unlock the valuable business insights trapped in data.
Try It Now »
sambanova-logo-black
header lang header lang EN
Try It Now »
Try It Now »

Does reduced precision hurt? A bit about losing bits.

Posted by Etash Guha on June 20, 2024

Recent work highlighted how quantization for recent LLaMa 3 models can lead to non-negligible decay in model performance. Does reduced precision hurt model performance?

Topics: technology, Blog

logotype_sambanova_orange
Our Headquarters:
2200 Geng Road, Unit 100
Palo Alto, CA 94303
(650) 263-1153
Terms & Conditions Privacy Policy
Copyright © 2024 SambaNova Systems, Inc. All rights reserved

Products

Technology

Resources

About

Contact

Customers turn to SambaNova to quickly deploy state-of-the-art AI capabilities to meet the demands of the AI-enabled world. Our purpose-built enterprise-scale AI platform is the technology backbone for the next generation of AI computing. We enable customers to unlock the valuable business insights trapped in their data. Our flagship offering, SambaNova Suite, overcomes the limitations of legacy technology to power the large complex foundation models that enable customers to discover new services and revenue streams, and boost operational efficiency. Headquartered in Palo Alto, California, SambaNova Systems was founded in 2017 by industry luminaries, and hardware and software design experts from Sun/Oracle and Stanford University. Investors include SoftBank Vision Fund 2, funds and accounts managed by BlackRock, Intel Capital, GV, Walden International, Temasek, GIC, Redline Capital, Atlantic Bridge Ventures, Celesta, and several others.
Our Headquarters:
2200 Geng Road, Unit 100
Palo Alto, CA 94303
(650) 263-1153
Terms & Conditions Privacy Policy
Copyright © 2024 SambaNova
Systems, Inc. All rights reserved