CommunityNews

CommunityNews

LLM Paper on Mamba MoE: Jamba Technical Report from AI2

Jamba: A Hybrid Transformer-Mamba Language Model.
We present Jamba, a new base large language model based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. Specifically, Jamba interleaves blocks of Transformer and Mamba layers, enjoying the benefits of both model families. MoE is added in some of these layers to increase model capacity while keeping active parameter usage manageable. This flexible architecture allows resource- and objective-specific configurations. In the particular configuration we have implemented, we end up with a powerful model that fits in a single 80GB GPU. Built at large scale, Jamba provides high throughput and small memory footprint compared to vanilla Transformers, and at the same time state-of-the-art performance on standard language model benchmarks and long-context evaluations. Remarkably, the model presents strong results for up to 256K tokens context length. We study various architectural decisions, such as how to combine Transformer and Mamba layers, and how to mix experts, and show that some of them are crucial in large scale modeling. We also describe several interesting properties of these architectures which the training and evaluation of Jamba have revealed, and plan to release checkpoints from various ablation runs, to encourage further exploration of this novel architecture. We make the weights of our implementation of Jamba publicly available under a permissive license.

Read in full here:

This thread was posted by one of our members via one of our news source trackers.

Where Next?

Popular General Dev topics Top

First poster: bot
Hush Keyboards with Hushboard. Yesterday while surfing the ASCII highways of IRC (yes, IRC) a URL linking to a MacOS application scrolle...
New
First poster: Maartz
This Keyboard Lets People Type So Fast It’s Banned From Typing Competitions. A new peripheral lets you keep typing without ever lifting ...
New
First poster: malloryerik
GitHub - hlissner/doom-emacs: An Emacs framework for the stubborn martian hacker. An Emacs framework for the stubborn martian hacker - G...
New
First poster: bot
How a piece of advice became a lifestyle TABLE OF CONTENTS WHERE TO BEGIN… FIRST CONTACT PICKING EMACS FOR LIFE CHEATING ON EMACS SERE...
New
First poster: FatimaAdamu
Two US lawyers fined for submitting fake court citations from ChatGPT. Law firm also penalised after chatbot invented six legal cases th...
New
First poster: AstonJ
Jan | Rethink the Computer. Jan turns your computer into an AI machine by running LLMs locally on your computer. It’s a privacy-focus, l...
New
CommunityNews
Once you get good at Rust all of these problems will go away Rust being great at big refactorings solves a largely self-inflicted issues ...
New
First poster: dyowee
Software engineering job openings hit five-year low?. There are 35% fewer software developer job listings on Indeed today, than five yea...
New
First poster: chris.johan
Skype’s days appear to be numbered, as a hidden string in the latest Skype for Windows preview suggests Microsoft will shutter the servic...
New
CommunityNews
Rendering Action Mailer emails with Phlex components and layouts: Clean, Composable, and Completely Ruby - Blog post by Camillo Visini
New

Other popular topics Top

AstonJ
What chair do you have while working… and why? Is there a ‘best’ type of chair or working position for developers?
New
AstonJ
You might be thinking we should just ask who’s not using VSCode :joy: however there are some new additions in the space that might give V...
New
PragmaticBookshelf
Rust is an exciting new programming language combining the power of C with memory safety, fearless concurrency, and productivity boosters...
New
AstonJ
Thanks to @foxtrottwist’s and @Tomas’s posts in this thread: Poll: Which code editor do you use? I bought Onivim! :nerd_face: https://on...
New
PragmaticBookshelf
Learn different ways of writing concurrent code in Elixir and increase your application's performance, without sacrificing scalability or...
New
New
gagan7995
API 4 Path: /user/following/ Method: GET Description: Returns the list of all names of people whom the user follows Response [ { ...
New
husaindevelop
Inside our android webview app, we are trying to paste the copied content from another app eg (notes) using navigator.clipboard.readtext ...
New
DevotionGeo
I have always used antique keyboards like Cherry MX 1800 or Cherry MX 8100 and almost always have modified the switches in some way, like...
New
AstonJ
This is a very quick guide, you just need to: Download LM Studio: https://lmstudio.ai/ Click on search Type DeepSeek, then select the o...
New