Nvidia Nemotron Nano

Définition

XXXXXXXXX

Français

Nemotron Nano 2 

Anglais

Nemotron Nano 2 

A hybrid Mamba-Transformer language model that combines high accuracy with significantly improved inference speed for reasoning tasks. The model achieves comparable or better performance than existing models while delivering up to 6× higher throughput for generation-heavy scenarios. This work demonstrates how architectural innovations can make advanced reasoning models more practical for real-world deployment.

Source

Source : huggingface