Update cli-api-guide.md

grammar nits

docs/cli-api-guide.md

@@ -19,20 +19,19 @@ limitations under the License.
 
 The Sparsify CLI/API is a Python package that allows you to run Sparsify Experiments locally, sync with the Sparsify Cloud, and integrate into your own workflows.
 
-## Install Sparsify
+## Installing Sparsify
 
-Next, you'll need to install Sparsify on your training hardware.
-To do this, run the following command:
+Next, install Sparsify on your training hardware by running the following command:
 
 ```bash
 pip install sparsify-nightly
 ```
 
 For more details and system/hardware requirements, see the [Installation](https://github.com/neuralmagic/sparsify#installation) section.
 
-## Login to Sparsify
+## Logging in to Sparsify
 
-With Sparsify installed on your training hardware, you'll need to authorize the local CLI to access your account.
+With Sparsify installed on your training hardware, you will need to authorize the local CLI to access your account.
 This is done by running the `sparsify.login` command and providing your API key.
 Locate your API key on the home page of the [Sparsify Cloud](https://apps.neuralmagic.com/sparsify) under the **'Get set up'** modal.
 Once you have located this, copy the command or the API key itself and run the following command:
@@ -41,19 +40,19 @@ Once you have located this, copy the command or the API key itself and run the f
 sparsify.login API_KEY
 ````
 
-The `sparsify.login API_KEY` command is used to sync your local training environment with the Sparsify Cloud in order to keep track of your Experiments. Once you run the `sparsify.login API_KEY` command, you should see a confirmation via the console that you are logged into Sparsify. To log out of Sparsify, use the `exit` command. 
+The `sparsify.login API_KEY` command is used to sync your local training environment with the Sparsify Cloud in order to keep track of your Experiments. Once you run the `sparsify.login API_KEY` command, you should see a confirmation via the console that you are logged in to Sparsify. To log out of Sparsify, use the `exit` command. 
 
 If you encounter any issues with your API key, reach out to the team via the [nm-sparsify Slack Channel](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-1xkdlzwv9-2rvS6yQcCs7VDNUcWxctnw), [email](mailto::rob@neuralmagic.com) or via [GitHub Issues](https://github.com/neuralmagic/sparsify/issues). 
 
 
-## Run an Experiment 
+## Running an Experiment 
 
 Experiments are the core of sparsifying a model. 
 They are the process of applying sparsification algorithms in One-Shot, Training-Aware, or Sparse-Transfer to a dataset and model.
 
-All Experiments are run locally on your training hardware and can be synced with the cloud for further analysis and comparison.
+All Experiments are run locally on your training hardware and can be synced with Sparsify Cloud for further analysis and comparison.
 
-To run an Experiment, you can use either the CLI or the API depending on your use case.
+To run an Experiment, you can use either the CLI or the API, depending on your use case.
 The Sparsify Cloud provides a UI for exploring hyperparameters, predicting performance, and generating the desired CLI/API command.
 
 The general command for running an Experiment is:
@@ -65,11 +64,11 @@ sparsify.run EXPERIMENT_TYPE --use-case USE_CASE --model MODEL --data DATA --opt
 Where the values for each of the arguments follow these general rules:
 - EXPERIMENT_TYPE: one of `one-shot`, `training-aware`, or `sparse-transfer`.
 
-- USE_CASE: the use case you're solving for such as `image-classification`, `object-detection`, `text-classification`, a custom use case, etc. A full list of supported use cases for each Experiment type can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/use-cases-guide.md).
+- USE_CASE: the use case you're solving for, such as `image-classification`, `object-detection`, `text-classification`, a custom use case, etc. A full list of supported use cases for each Experiment type can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/use-cases-guide.md).
   
-- MODEL: the model you want to sparsify which can be a model name such as `resnet50`, a stub from the [SparseZoo](https://sparsezoo.neuralmagic.com), or a path to a local model. For One-Shot, currently the model must be in an ONNX format. For Training-Aware and Sparse-Transfer, the model must be in a PyTorch format. More details on model formats can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/models-guide.md).
+- MODEL: the model you want to sparsify which can be a model name such as `resnet50`, a stub from the [SparseZoo](https://sparsezoo.neuralmagic.com), or a path to a local model. For One-Shot, currently, the model must be in an ONNX format. For Training-Aware and Sparse-Transfer, the model must be in a PyTorch format. More details on model formats can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/models-guide.md).
   
-- DATA: the dataset you want to use to the sparsify the model. This can be a dataset name such as `imagenette` or a path to a local dataset. Currently, One-Shot only supports NPZ formatted datasets. Training-Aware and Sparse-Transfer support PyTorch ImageFolder datasets for image classification, YOLOv5/v8 datasets for object detection and segmentation, and HuggingFace datasets for NLP/NLG. More details on dataset formats can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/datasets-guide.md).
+- DATA: the dataset you want to use to sparsify the model. This can be a dataset name such as `imagenette` or a path to a local dataset. Currently, One-Shot only supports NPZ formatted datasets. Training-Aware and Sparse-Transfer support PyTorch ImageFolder datasets for image classification, YOLOv5/v8 datasets for object detection and segmentation, and Hugging Face datasets for NLP/NLG. More details on dataset formats can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/datasets-guide.md).
   
 - OPTIM_LEVEL: the desired sparsification level from 0 (none) to 1 (max). The general rule is that 0 is the baseline model, <0.3 only quantizes the model, 0.3-1.0 increases the sparsity of the model and applies quantization. More details on sparsification levels can be found [here](https://github.com/neuralmagic/sparsify/blob/main/docs/optim-levels-guide.md).
 
@@ -82,10 +81,10 @@ Where the values for each of the arguments follow these general rules:
 | **++**   | **+++++**            | **+++**  |
 
 One-Shot Experiments are the quickest way to create a faster and smaller version of your model.
-The algorithms are applied to the model post training utilizing a calibration dataset, so they result in no further training time and much faster sparsification times compared with Training-Aware Experiments.
+The algorithms are applied to the model post-training, utilizing a calibration dataset, so they result in no further training time and much faster sparsification times compared with Training-Aware Experiments.
 
 Generally, One-Shot Experiments result in a 3-5x speedup with minimal accuracy loss.
-They are ideal for when you want to quickly sparsify your model and don't have a lot of time to spend on the sparsification process.
+They are ideal for when you want to quickly sparsify your model and have limited time to spend on the sparsification process.
 
 CV Example:
 ```bash
@@ -149,7 +148,7 @@ sparsify.run training-aware --use-case text_classification --model bert-base --d
 Landing Soon!
 
 
-## Compare the Experiment results
+## Comparing the Experiment results
 
 Once you have run your Experiment, you can compare the results printed out to the console using the `deepsparse.benchmark` command. 
 In the near future, you will be able to compare the results in the Cloud, measure other scenarios, and compare the results to other Experiments.