view article Article Google Released Gemma-4 Four Days Ago. We Already Made It 1.72× Faster. lujangusface • Apr 7 • 2
view article Article Open-source DeepResearch – Freeing our search agents +3 m-ric, albertvillanova, merve, thomwolf, clefourrier • Feb 4, 2025 • 1.32k
Llama 3.2 Collection This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 673
Meta-Llama-3.1-Quantized Collection Collection of quantized Llama 3.1 models (8B & 70B versions for now), using bitsandbites. • 4 items • Updated Aug 28, 2024 • 1
view article Article A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes ybelkada, timdettmers • Aug 17, 2022 • 132