#fine
6 discoveries · Hand-picked discoveries from the open web, newest first.
-
Why your fine-tuning job takes longer than the FLOPs say
A Blog post by Dharma-AI on Hugging Face
Hugging Face Blog · EN
-
Homeopathic Learning: Diluting Poisoned Fine-Tuning Data Can Strengthen Its Effect
Authors: Matt Clarke *, Jan Dubiński *, James Chua , Simon Schrodi , Owain Evans , Alex Cloud (*- Core contribution) tl;dr. We find that poisoned training data with little effect on its own can create a hidden backdoor once clean, contrasting data is added. We demonstrate this effect in small models fine-tuned on datasets we constructed. 📄 Paper , 💻 Code , 🐦 Twitter Work done as part of the Anthropic Fellows Program , in collaboration with Truthful AI . This article is cross-posted from the Anthropic Alignment Science Blog . Paper abstract We study homeopathic learning , a phenomenon where
LessWrong · EN
-
Double Fine выпустила крупное обновления для Kiln, но онлайн игры в Steam достиг нуля
Обновление Kiln от Double Fine, новый режим, локальный кооператив, отсутствие интереса, пиковый онлайн ноль, игра не вышла в российском Steam
DTF · RU
-
The Definitive Fine-Tuning Guide for 3D Generation Models
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog · EN
-
Packaging Design: LeNOSE Fine Fragrance Hand Soap Identity
Explore LeNOSE's witty packaging design and fine fragrance development, pairing geometric die-cut labels with $10 luxury hand soaps. Somewhere over the last decade, washing your hands turned into a bi...
Abduzeedo · EN
-
Fine – Sometimes i rush
Video by Betty Krag . Fine 's Jazz Dreams is out October 23rd ... Continue reading…
Gorilla vs Bear · EN