Patrick Devaney's picture

Patrick Devaney

patrickbdevaney

·

AI & ML interests

mamba s4, mixtral 8x-7b, candle, pytorch

Recent Activity

liked a model 2 days ago

Qwen/Qwen3.5-0.8B

liked a model 2 days ago

Qwen/Qwen3.5-2B

liked a model 2 days ago

Qwen/Qwen3.5-4B

View all activity

Organizations

upvoted a collection 2 days ago

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 15 items • Updated about 2 hours ago • 235

upvoted 2 collections 10 days ago

Nemotron-Pre-Training-Datasets

Large scale pre-training datasets used in the Nemotron family of models. • 12 items • Updated about 2 hours ago • 128

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano and Super v3. • 28 items • Updated about 2 hours ago • 98

upvoted a collection 17 days ago

Nemotron-H

Mamba-Transformer hybrid models • 10 items • Updated about 2 hours ago • 32

upvoted an article 10 months ago

Article

The Transformers Library: standardizing model definitions

+2

May 15, 2025

•

121

upvoted an article over 1 year ago

Article

Welcome Falcon Mamba: The first strong attention-free 7B model

+4

Aug 12, 2024

•

113

upvoted a collection over 1 year ago

Image to 3D

11 items • Updated Aug 20, 2024 • 8