From a56a63b285c4ce91578d5bd2492cacac01b7ceda Mon Sep 17 00:00:00 2001 From: Alexandre Strube <a.strube@fz-juelich.de> Date: Tue, 3 Dec 2024 20:49:16 +0100 Subject: [PATCH] Revise content in index.md and index.html for non-transformer architectures, updating examples and improving clarity --- index.md | 6 ++++-- public/index.html | 9 ++++++--- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/index.md b/index.md index 42d81d3..9e099df 100644 --- a/index.md +++ b/index.md @@ -200,11 +200,13 @@ date: December 4th, 2024 # Non-transformer architectures -- Last I checked, Jamba 1.5 was the best one +- First one was Mamba in February +- Jamba from A21 in March +- Last I checked, LFM 40B MoE from Liquid/MIT was the best one (from 30.09) - Performs well on benchmarks - What about real examples? - Some mathematical discussions about it being turing-complete (probably not) -- Other examples are Hymba from NVIDIA, Liquid from MIT +- Other example is Hymba from NVIDIA (tiny model, 1.5B) --- diff --git a/public/index.html b/public/index.html index a046cd1..e7d0b8c 100644 --- a/public/index.html +++ b/public/index.html @@ -489,13 +489,16 @@ across continents and 96% when training only in the USA</li> <section id="non-transformer-architectures" class="slide level1"> <h1>Non-transformer architectures</h1> <ul> -<li class="fragment">Last I checked, Jamba 1.5 was the best one</li> +<li class="fragment">First one was Mamba in February</li> +<li class="fragment">Jamba from A21 in March</li> +<li class="fragment">Last I checked, LFM 40B MoE from Liquid/MIT was the +best one (from 30.09)</li> <li class="fragment">Performs well on benchmarks</li> <li class="fragment">What about real examples?</li> <li class="fragment">Some mathematical discussions about it being turing-complete (probably not)</li> -<li class="fragment">Other examples are Hymba from NVIDIA, Liquid from -MIT</li> +<li class="fragment">Other example is Hymba from NVIDIA (tiny model, +1.5B)</li> </ul> </section> <section id="eu-ai-act" class="slide level1"> -- GitLab