Fixing a broken header

Author: mattmcinnes

articles/virtual-machines/sizes/gpu-accelerated/nd-family.md

@@ -9,15 +9,15 @@ ms.date: 04/18/2024
 ms.author: mattmcinnes
 ---
 
-# 'NC' sub-family GPU accelerated VM size series
+# 'ND' sub-family GPU accelerated VM size series
 
 **Applies to:** :heavy_check_mark: Linux VMs :heavy_check_mark: Windows VMs :heavy_check_mark: Flexible scale sets :heavy_check_mark: Uniform scale sets
 
 The 'ND' family of VM size series are one of Azure's GPU-accelerated VM instances. They're designed for deep learning, AI research, and high-performance computing tasks that benefit from powerful GPU acceleration. Equipped with NVIDIA GPUs, ND-series VMs offer specialized capabilities for training and inference of complex machine learning models, facilitating faster computations and efficient handling of large datasets. This makes them particularly well-suited for academic and commercial applications in AI development and simulation, where cutting-edge GPU technology is crucial for achieving rapid and accurate results in neural network processing and other computationally intensive tasks.
 
 ## Workloads and use cases
 
-**AI and Deep Learning:** ND-family VMs are ideal for training and deploying complex deep learning models. Equipped with powerful NVIDIA Tesla GPUs, they provide the computational power necessary for handling extensive neural network training with large datasets, significantly reducing training times.
+**AI and Deep Learning:** ND-family VMs are ideal for training and deploying complex deep learning models. Equipped with powerful NVIDIA GPUs, they provide the computational power necessary for handling extensive neural network training with large datasets, significantly reducing training times.
 
 **High-Performance Computing (HPC):** ND-family VMs are suitable for HPC applications that require GPU acceleration. Fields such as scientific research, engineering simulations (e.g., computational fluid dynamics), and genomic processing can benefit from the high-throughput computing capabilities of ND-series VMs.