Picture for Jinze Xue

Jinze Xue

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Add code
Aug 21, 2025
Viaarxiv icon

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

Add code
Apr 10, 2025
Viaarxiv icon

Methods of improving LLM training stability

Add code
Oct 22, 2024
Figure 1 for Methods of improving LLM training stability
Figure 2 for Methods of improving LLM training stability
Figure 3 for Methods of improving LLM training stability
Figure 4 for Methods of improving LLM training stability
Viaarxiv icon