Sam Foreman

samforeman

AI & ML interests

{ AI for Science, LLMs @ Scale, Generative Modeling for Physics / Lattice QCD } @ Argonne National Laboratory https://alcf.anl.gov/about/people/sam-foreman

Recent Activity

upvoted a paper 11 days ago

OmniSVG: A Unified Scalable Vector Graphics Generation Model

liked a Space 20 days ago

nanotron/ultrascale-playbook

liked a dataset 22 days ago

nanotron/ultrascale-playbook-data

View all activity

Organizations

samforeman's activity

upvoted a paper 11 days ago

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published 13 days ago • 146

liked a Space 20 days ago

2.49k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a dataset 22 days ago

nanotron/ultrascale-playbook-data

Updated Mar 12 • 11.7k • 5

reacted to giux78's post with ❤️ 22 days ago

Post

3180

This is truly an inspirational story please help us spread the word, @clem , @thomwolf and everyone who supports open source AI.

A few weeks ago, @mmuffo94 and @cittiberto from indigo_ai launched the Chatbot Arena for the Italian language: https://indigo.ai/it/chatbot-arena-italia/.

To our surprise, among the top-ranked models is mii-llm/maestrale-chat-v0.4-beta a carefully fine-tuned version of mistralai/Mistral-7B-v0.1, developed by @efederici and @mferraretto from

mii-llm , and released nearly a year ago.

At this very moment, as shown in the screenshot, mii-llm/maestrale-chat-v0.4-beta is ranked 8th right between ChatGPT-4.5 and ChatGPT-4o.

It's likely that for several months, the best Italian speaking LLM has been an open source 7B model created by open source contributors and hardly anyone knew it.