Blog 2
Use this space to tell everyone about what you have to offer.
Does reduced precision hurt? A bit about losing bits.
SambaNova and Groq recently achieved 1000 tokens per second on their inference system for Meta’s LLaMa 3 8b Instruct...
Introducing Fugaku-LLM in Composition of Experts
The Composition of Experts (CoE) architecture that the Samba-1 model is based upon has many features that make it...
Sovereign AI: Full-Stack Infrastructure for AI Autonomy
Artificial intelligence has become vital to nations, governments, and large corporations. Many of these large...
NAIRR; Govt-funded AI Research Resources
Artificial intelligence (AI) is driving the next generation of technological innovation and scientific discovery....
Tokens Per Second is Not All You Need
In the fast-paced world of LLM inference, there's been a growing buzz around achieving high tokens per second...
Samba-CoE v0.3: The Power of Routing ML Models at Scale
*A twitter user said that CausalLM-34b-beta is suspected to have MMLU contamination. On further investigation we do...
Responsible AI
Generative AI will be the defining technology of this century, fundamentally reshaping how businesses, governments,...
SambaLingo hits 15,000+ downloads, now integrated with Samba-CoE-v0.2
SambaLingo, our cutting-edge multilingual language expert series, surpassed 15k downloads and is now integrated into...
AI Power: Accurate Models at Blazing Speeds | SambaNova
In late February, we announced Samba-1, a CoE architecture that is a paradigm-shift, and will ultimately become the...
Using Mixed Precision on RDUs
Deep learning frameworks have traditionally relied upon the 32-bit single-precision (FP32) format. However, FP32...
Benchmarking Samba-1
Today, we announced Samba-1, a Composition of Experts model with over 1 trillion parameters, built on top of open...
Samba-CoE v0.1: Unlocking the Power of Experts
We're thrilled to unveil Samba-CoE-v0.1, a scaled down version of Samba-1, our latest breakthrough model that...
High-Accuracy AI Models in 9 Languages
SambaNova is excited to open source a collection of expert models that adapt Llama 2 [12] to a diverse set of 9...
SambaCoder-nsql-Llama-2-70B model
Using a Text-to-SQL generative AI solution can have a significant impact on enterprise organizations. This will...
BLOOMChat-v2 Long Sequences at 176B
We are proud to release BLOOMChat-v2, a 32K sequence length, 176B multilingual language model trained on top of...
SambaNova RDAs: Mastering Fault Management (Part 2)
In Part 1 of this two-part blog, we discussed the SambaNova product components, discussed some fault management...
SambaNova RDAs: Mastering Fault Management (Part 1)
SambaNova delivers the first, full stack enterprise grade generative AI platform. Designed specifically for the...
ALiBi Deep Dive: Interpolation vs. Extrapolation
Introduction Long sequence capabilities enable a variety of applications like summarizing long form documents, such...
Elevating Information Retrieval and Augmenting Large Language Models
We are pleased to announce that SambaStudio now supports text embedding models. This new feature significantly...
Enabling Open Source LLMs to Become Effective Tool Manipulators
INTRODUCTION Using tools can extend the capabilities of LLMs’ to access knowledge beyond their training data. As an...
Training long sequence size models with SambaNova
At SambaNova, we have been researching and developing methods to train long sequence size (SS) models on our...
BLOOMChat: Open-Source Multilingual Chat LLM
[1] The image is created with Midjourney Highlights SambaNova, in collaboration with Together, is excited to present...
Subscribe
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nullam ultrices massa sit amet auctor scelerisque. Cras vel quam non lorem tincidunt facilisis.