Broken Links FIx/Misc Typos/Omissions (#107)

Corrected broken links, grammar, typos:

* Update deepsparse.mdx

* Update custom-integrations.mdx

* Update deploying.mdx

* Update diagnotistics-debugging.mdx

* Update sparsezoo.mdx

* Update sparseml.mdx

* Update deepsparse-ent.mdx

* Update sparsezoo.mdx

updating missing sparsezoo links that were broken; pointing to GitHub for now until next gen SparseZoo design is more realized

meta description not filled in correctly

* Update gatsby-node.js

old supported hardware URL heavily referenced

Author: jeanniefinks

gatsby-node.js

@@ -44,6 +44,7 @@ exports.createPages = ({ graphql, actions }) => {
         });
 
         // create redirect pages
+        createRedirect({ fromPath: '/deepsparse/source/hardware.html', toPath: '/user-guide/deepsparse-engine/hardware-support', redirectInBrowser: true, isPermanent: true });
         createRedirect({ fromPath: '/deepsparse', toPath: '/products/deepsparse', redirectInBrowser: true, isPermanent: true });
         createRedirect({ fromPath: '/sparseml', toPath: '/products/sparseml', redirectInBrowser: true, isPermanent: true });
         createRedirect({ fromPath: '/sparsezoo', toPath: '/products/sparsezoo', redirectInBrowser: true, isPermanent: true });

src/content/get-started/sparsify-a-model/custom-integrations.mdx

@@ -9,7 +9,7 @@ index: 2000
 # Creating a Custom Integration for Sparsifying Models
 
 This page explains how to apply a recipe to a custom model. For more details on the concepts of pruning/quantization
-as well as how to create recipes, see the [prior page](/get-started/transfer-a-sparsified-model).
+as well as how to create recipes, see [Sparsifying a Model for SparseML Integrations](/get-started/sparsify-a-model/supported-integrations).
 
 In addition to supported integrations described on the prior page, SparseML is set to enable easy integration in custom training pipelines.
 This flexibility enables easy sparsification for any neural network architecture for custom models and use cases. Once SparseML is installed,
@@ -56,7 +56,7 @@ from sparseml.pytorch.datasets import ImagenetteDataset, ImagenetteSize
 from sparseml.pytorch.optim import ScheduledModifierManager
 
 # Model creation
-NUM_CLASSES = 10  # number of imagenette classes
+NUM_CLASSES = 10  # number of Imagenette classes
 model = resnet50(pretrained=True, num_classes=NUM_CLASSES)
 
 # Dataset creation
@@ -72,7 +72,7 @@ model.to(device)
 criterion = CrossEntropyLoss()
 optimizer = SGD(model.parameters(), lr=10e-6, momentum=0.9)
 
-# Recipe - in this case, we pull down a recipe from the SparseZoo for ResNet50
+# Recipe - in this case, we pull down a recipe from the SparseZoo for ResNet-50
 # This can be a be a path to a local file
 recipe_path = "zoo:cv/classification/resnet_v1-50/pytorch/sparseml/imagenet/pruned95_quant-none?recipe_type=original"
 
@@ -106,8 +106,8 @@ manager.finalize(model)
 
 ## Create a Recipe
 
-The recipe used in the supported integrations page will also work for custom integrations.
-To dive into the details of this recipe and how to edit it, visit [the prior page](/get-started/supported-integrations).
+<!-- The recipe used in the [Supported Integrations page](get-started/sparsify-a-model/supported-integrationsget-started/sparsify-a-model/supported-integrationsget-started/sparsify-a-model/supported-integrations) will also work for custom integrations. -->
+To dive into the details of this recipe and how to edit it, visit [Supported Integrations](/get-started/sparsify-a-model/supported-integrations).
 The resulting recipe is included here for easy integration and testing.
 
 ```yaml

src/content/products/deepsparse-ent.mdx

@@ -43,7 +43,7 @@ index: 2000
   </div>
 </div>
 
-A CPU runtime that takes advantage of sparsity within neural networks to reduce compute. Read more about sparsification [here](https://docs.neuralmagic.com/main/source/getstarted.html#sparsification).
+A CPU runtime that takes advantage of sparsity within neural networks to reduce compute. Read [more about sparsification](user-guide/deepsparse-engine/hardware-support).
 
 Neural Magic's DeepSparse Engine is able to integrate into popular deep learning libraries (e.g., Hugging Face, Ultralytics) allowing you to leverage DeepSparse for loading and deploying sparse models with ONNX.
 ONNX gives the flexibility to serve your model in a framework-agnostic environment.
@@ -61,7 +61,7 @@ The DeepSparse Engine is available in two editions:
 
 ## 🧰 Hardware Support and System Requirements
 
-Review [CPU Hardware Support for Various Architectures](https://docs.neuralmagic.com/deepsparse/source/hardware.html) to understand system requirements.
+Review [Supported Hardware for the DeepSparse Engine](user-guide/deepsparse-engine/hardware-support) to understand system requirements.
 The DeepSparse Engine works natively on Linux; Mac and Windows require running Linux in a Docker or virtual machine; it will not run natively on those operating systems.
 
 The DeepSparse Engine is tested on Python 3.7-3.10, ONNX 1.5.0-1.12.0, ONNX opset version 11+, and manylinux compliant.
@@ -75,7 +75,7 @@ Install the Enterprise Edition as follows:
 pip install deepsparse-ent
 ```
 
-See the [DeepSparse Enterprise Installation Page](https://docs.neuralmagic.com/get-started/install/deepsparse-ent) for further installation options.
+See the [DeepSparse Enterprise Installation Page](/get-started/install/deepsparse-ent) for further installation options.
 
 ## Getting a License
 

src/content/products/deepsparse.mdx

@@ -43,7 +43,7 @@ index: 1000
   </div>
 </div>
 
-A CPU runtime that takes advantage of sparsity within neural networks to reduce compute. Read more about sparsification [here](https://docs.neuralmagic.com/main/source/getstarted.html#sparsification).
+A CPU runtime that takes advantage of sparsity within neural networks to reduce compute. Read [more about sparsification](https://docs.neuralmagic.com/user-guide/sparsification).
 
 Neural Magic's DeepSparse Engine is able to integrate into popular deep learning libraries (e.g., Hugging Face, Ultralytics) allowing you to leverage DeepSparse for loading and deploying sparse models with ONNX.
 ONNX gives the flexibility to serve your model in a framework-agnostic environment.
@@ -61,7 +61,7 @@ The DeepSparse Engine is available in two editions:
 
 ## 🧰 Hardware Support and System Requirements
 
-Review [CPU Hardware Support for Various Architectures](https://docs.neuralmagic.com/deepsparse/source/hardware.html) to understand system requirements.
+Review [Supported Hardware for the DeepSparse Engine](https://docs.neuralmagic.com/user-guide/deepsparse-engine/hardware-support) to understand system requirements.
 The DeepSparse Engine works natively on Linux; Mac and Windows require running Linux in a Docker or virtual machine; it will not run natively on those operating systems.
 
 The DeepSparse Engine is tested on Python 3.7-3.10, ONNX 1.5.0-1.12.0, ONNX opset version 11+, and manylinux compliant.
@@ -77,7 +77,7 @@ pip install deepsparse
 
 See the [DeepSparse Community Installation Page](https://docs.neuralmagic.com/get-started/install/deepsparse) for further installation options.
 
-To trial or inquire about licensing for DeepSparse Enterprise Edition, see the [DeepSparse Enterprise documentation](https://docs.neuralmagic.com/products/deepsparse-enterprise).
+To trial or inquire about licensing for DeepSparse Enterprise Edition, see the [DeepSparse Enterprise documentation](https://docs.neuralmagic.com/products/deepsparse-ent).
 
 ## Features
 

src/content/products/sparseml.mdx

@@ -50,7 +50,7 @@ SparseML is a toolkit that includes APIs, CLIs, scripts and libraries that enabl
 SparseML provides two options to accomplish this goal:
 - **Sparse Transfer Learning**: Fine-tune state-of-the-art pre-sparsified models from the SparseZoo onto your dataset while preserving sparsity.
 
-- **Sparsifying from Scratch**: Apply state-of-the-art [sparsification](https://docs.neuralmagic.com/main/source/getstarted.html#sparsification) algorithms such as pruning and quantization to any neural network.
+- **Sparsifying from Scratch**: Apply state-of-the-art [sparsification](/user-guide/sparsification) algorithms such as pruning and quantization to any neural network.
 
 These options are useful for different situations:
 - **Sparse Transfer Learning** is the easiest path to creating a sparse model trained on your data. Pull down a sparse model from SparseZoo and point our training scripts at your data without any hyperparameter search. This is the recommended pathway for supported use cases like Image Classification, Object Detection, and several NLP tasks.
@@ -59,58 +59,59 @@ These options are useful for different situations:
 
 Each of these avenues use YAML-based **recipes** that simplify integration with popular deep learning libraries and framrworks.
 
-<img alt="SparseML Flow" src="https://docs.neuralmagic.com/docs/source/infographics/sparseml.png" width="100%" style={{maxWidth: "100%"}} />
-
+<img src="https://docs.neuralmagic.com/docs/source/infographics/sparseml.png" alt="SparseML Flow" />
+ 
+ 
 ## Highlights
 
 ### Integrations
 
 <p>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/pytorch">
-    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/pytorch-torchvision.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/pytorch-torchvision.png" alt="Integration - PyTorch: MobileNetV1, ResNet-50" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/ultralytics-yolov3">
-    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/ultralytics-yolov3.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/ultralytics-yolov3.png" alt="Integration - Ultralytics: YOLOv3" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/ultralytics-yolov5">
-    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/ultralytics-yolov5.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/ultralytics-yolov5.png" alt="Integration - Ultralytics: YOLOv5" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/huggingface-transformers">
-    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/huggingface-transformers.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/huggingface-transformers.png" alt="Integration - Hugging Face: BERT" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/rwightman-timm">
-    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/rwightman-timm.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/highlights/sparseml/rwightman-timm.png" alt="Integration - rwightman: ResNet-50" width="136px" />
   </a>
 </p>
 
 ### Creating Sparse Models
 
 <p>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/pytorch/notebooks/classification.ipynb">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/classification_resnet-50.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/classification_resnet-50.png" alt="Creating Sparse ResNet-50" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/ultralytics-yolov3/tutorials/sparsifying_yolov3_using_recipes.md">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov3.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov3.png" alt="Creating Sparse YOLOv3" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/ultralytics-yolov5/tutorials/sparsifying_yolov5_using_recipes.md">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov5.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov5.png" alt="Creating Sparse YOLOv5" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/huggingface-transformers/tutorials/sparsifying_bert_using_recipes.md">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/nlp_bert.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/nlp_bert.png" alt="Creating Sparse BERT" width="136px" />
   </a>
 </p>
 
 ### Transfer Learning from Sparse Models
 
 <p>
   <a href="https://github.com/neuralmagic/sparseml/tree/main/integrations/pytorch/notebooks/sparse_quantized_transfer_learning.ipynb">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/classification_resnet-50.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/classification_resnet-50.png" alt="Transfer Learn - ResNet-50" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov3/tutorials/yolov3_sparse_transfer_learning.md">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov3.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov3.png" alt="Transfer Learn - YOLOv3" width="136px" />
   </a>
   <a href="https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/tutorials/yolov5_sparse_transfer_learning.md">
-    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov5.png" width="136px" />
+    <img src="https://docs.neuralmagic.com/docs/source/tutorials/detection_yolov5.png" alt="Transfer Learn - YOLOv5" width="136px" />
   </a>
 </p>
 
@@ -188,7 +189,7 @@ $ sparseml.yolov5.train \
     --recipe zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95
 ```
 
-For more details on the above as well as examples for more supported use cases see [here](/use-cases/natural-language-processing/question-answering).
+[See more details](/use-cases/natural-language-processing/question-answering) on the above as well as examples for more supported use cases.
 
 #### For Custom Use Cases / Supported Use Cases: Python Integration
 

src/content/products/sparsezoo.mdx

@@ -1,7 +1,7 @@
 ---
 title: "SparseZoo"
 metaTitle: "SparseZoo"
-metaDescription: "SparseZoo"
+metaDescription: "Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes"
 githubURL: "Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes"
 index: 4000
 ---
@@ -47,7 +47,7 @@ index: 4000
 
 [SparseZoo is a constantly-growing repository](https://sparsezoo.neuralmagic.com) of sparsified (pruned and pruned-quantized) models with matching sparsification recipes for neural networks.
 It simplifies and accelerates your time-to-value in building performant deep learning models with a collection of inference-optimized models and recipes to prototype from.
-Read more about sparsification [here.](https://docs.neuralmagic.com/main/source/getstarted.html#sparsification)
+Read [more about sparsification.](/user-guide/sparsification)
 
 Available via API and hosted in the cloud, the SparseZoo contains both baseline and models sparsified to different degrees of inference performance vs. baseline loss recovery.
 Recipe-driven approaches built around sparsification algorithms allow you to use the models as given, transfer-learn from the models onto private datasets, or transfer the recipes to your architectures.
@@ -58,8 +58,8 @@ The [GitHub repository](https://github.com/neuralmagic/sparsezoo) contains the P
 
 ## Highlights
 
-- [Model Stub Architecture Overview](https://docs.neuralmagic.com/sparsezoo/source/models.html)
-- [Available Model Recipes](https://docs.neuralmagic.com/sparsezoo/source/recipes.html)
+- [Model Stub Architecture Overview](https://github.com/neuralmagic/sparsezoo/blob/main/docs/source/models.md)
+- [Available Model Recipes](https://github.com/neuralmagic/sparsezoo/blob/main/docs/source/recipes.md)
 - [sparsezoo.neuralmagic.com](https://sparsezoo.neuralmagic.com)
 
 ## Installation

src/content/use-cases/image-classification/deploying.mdx

@@ -20,7 +20,7 @@ This section requires the [DeepSparse Server Install](/get-started/install/deeps
 ## Getting Started
 
 Before you start using the DeepSparse Engine, confirm your machine is
-compatible with our [hardware requirements](https://docs.neuralmagic.com/deepsparse/source/hardware.html).
+compatible with our [hardware requirements](/user-guide/deepsparse-engine/hardware-support).
 
 ### Model Format
 
@@ -71,7 +71,7 @@ The examples below use option 2. However, you can pass the local path to the ONN
 DeepSparse provides both a Python `Pipeline` API and an out-of-the-box model
 server that can be used for end-to-end inference in either Python
 workflows or as an HTTP endpoint. Both options provide similar specifications
-for configurations and support a variety of Image Classification models.
+for configurations and support a variety of image classification models.
 
 ### Python API
 
@@ -94,10 +94,10 @@ serve ONNX models and pipelines in HTTP. Configuring the server uses the same pa
 enabling simple deployment. Once launched, a `/docs` endpoint is created with full
 endpoint descriptions and support for making sample requests.
 
-An example deployment using a 95% pruned ResNet50 is given below.
+An example deployment using a 95% pruned ResNet-50 is given below.
 
 For full documentation on deploying sparse image classification models with the
-DeepSparse Server, see the [documentation for DeepSparse Server](/user-cases/deploying-deepsparse/deepsparse-server).
+DeepSparse Server, see the [documentation for DeepSparse Server](/use-cases/deploying-deepsparse/deepsparse-server).
 
 ## Deployment Examples
 
@@ -107,8 +107,8 @@ but a local path to an ONNX file can also be passed as the `model_path`.
 
 ### Python API
 
-Create a `Pipeline` to run inference with the following code. The `Pipeline` handles the pre-processing (e.g. subtracting by ImageNet 
-means, dividing by ImageNet standard deviation) and post-processing so you can pass an raw image and recieve an class without any extra code.
+Create a `Pipeline` to run inference with the following code. The `Pipeline` handles the pre-processing (e.g., subtracting by ImageNet 
+means, dividing by ImageNet standard deviation) and post-processing so you can pass an raw image and receive an class without any extra code.
 
 ```python
 from deepsparse import Pipeline

src/content/user-guide/deepsparse-engine/diagnotistics-debugging.mdx

@@ -8,7 +8,7 @@ index: 4000
 
 # Logging Guidance for Diagnostics and Debugging
 
-This page explains the Diagnostics and Debugging features available in DeepSparse Engine.
+This page explains the diagnostics and debugging features available in DeepSparse Engine.
 
 Unlike traditional software, debugging utilities available to the machine learning community are scarce. Complicated with deployment pipeline design issues, model weights, model architecture, and unoptimized models, debugging performance issues can be very dynamic in your data science ecosystem. Reviewing a log file can be your first line of defense in pinpointing performance issues with optimizing your inference.
 
@@ -69,7 +69,7 @@ By default, logs will print out to the stderr of your process. If you would like
 
 ## Parsing an Example Log
 
-If you want to see an example log with `NM_LOGGING_LEVEL=diagnose`, a [truncated sample output](example-log.md) is provided at the end of this guide. It will show a super_resolution network, where Neural Magic only supports running 70% of it.
+If you want to see an example log with `NM_LOGGING_LEVEL=diagnose`, a truncated sample output is provided at the end of this guide. It will show a super_resolution network, where Neural Magic only supports running 70% of it.
 
 _Different portions of the log are explained below._
 
@@ -186,7 +186,7 @@ Locating  `== NM Execution Provider supports` shows how many subgraphs we compil
 
 ### Full Example Log, Verbose Level = diagnose
 
-The following is an example log with `NM_LOGGING_LEVEL=diagnose` running a super_resolution network, where we only support running 70% of it. Different portions of the log are explained in [Parsing an Example Log.](diagnostics-debugging.md#parsing-an-example-log)
+The following is an example log with `NM_LOGGING_LEVEL=diagnose` running a super_resolution network, where we only support running 70% of it. Different portions of the log are explained in [Parsing an Example Log.](/user-guide/deepsparse-engine/diagnotistics-debugging#parsing-an-example-log)
 
 ```text
 onnx_filename : test-models/cv-resolution/super_resolution/none-bsd300-onnx-repo/model.onnx