Update README.md

Fixed some potential misspellings.

Author: jun216tee

02-exploring-and-comparing-different-llms/README.md

@@ -21,7 +21,7 @@ This lesson will cover:
 After completing this lesson, you will be able to:
 
 - Select the right model for your use case.
-- Understand how to test, iterate, and improve performance of your model.
+- Understand how to test, iterate, and improve the performance of your model.
 - Know how businesses deploy models.
 
 ## Understand different types of LLMs
@@ -34,7 +34,7 @@ Depending on if you aim to use the models for text, audio, video, image generati
 
 - **Audio and speech recognition**. For this purpose, Whisper-type models are a great choice as they're general-purpose and aimed at speech recognition. It's trained on diverse audio and can perform multilingual speech recognition. Learn more about [Whisper type models here](https://platform.openai.com/docs/models/whisper?WT.mc_id=academic-105485-koreyst).
 
-- **Image generation**. For image generation, DALL-E and Midjourney are two very known choices. DALL-E is offered by Azure OpenAI. [Read more about DALL-E here](https://platform.openai.com/docs/models/dall-e?WT.mc_id=academic-105485-koreyst) and also in Chapter 9 of this curriculum.
+- **Image generation**. For image generation, DALL-E and Midjourney are two very well-known choices. DALL-E is offered by Azure OpenAI. [Read more about DALL-E here](https://platform.openai.com/docs/models/dall-e?WT.mc_id=academic-105485-koreyst) and also in Chapter 9 of this curriculum.
 
 - **Text generation**. Most models are trained on text generation and you have a large variety of choices from GPT-3.5 to GPT-4. They come at different costs with GPT-4 being the most expensive. It's worth looking into the [Azure OpenAI playground](https://oai.azure.com/portal/playground?WT.mc_id=academic-105485-koreyst) to evaluate which models best fit your needs in terms of capability and cost.
 
@@ -101,9 +101,9 @@ Imagine that we can have someone as well who could create and review the quiz, t
 
 Now, let's talk about the difference between a service and a model. A service is a product that is offered by a Cloud Service Provider, and is often a combination of models, data, and other components. A model is the core component of a service, and is often a foundation model, such as an LLM.
 
-Services are often optimized for production use and are often easier to use than models, via a graphical user interface. However, services are not always available for free, and may require a subscription or payment to use, in exchange for leveraging the service owner’s equipment and resources, optimizing expenses and scaling easily. An example of service is [Azure OpenAI Service](https://learn.microsoft.com/azure/ai-services/openai/overview?WT.mc_id=academic-105485-koreyst), which offers a pay-as-you-go rate plan, meaning users are charged proportionally to how much they use the service Also, Azure OpenAI Service offers enterprise-grade security and responsible AI framework on top of the models' capabilities.
+Services are often optimized for production use and are often easier to use than models, via a graphical user interface. However, services are not always available for free, and may require a subscription or payment to use, in exchange for leveraging the service owner’s equipment and resources, optimizing expenses and scaling easily. An example of a service is [Azure OpenAI Service](https://learn.microsoft.com/azure/ai-services/openai/overview?WT.mc_id=academic-105485-koreyst), which offers a pay-as-you-go rate plan, meaning users are charged proportionally to how much they use the service Also, Azure OpenAI Service offers enterprise-grade security and a responsible AI framework on top of the models' capabilities.
 
-Models are just the Neural Network, with the parameters, weights, and others. Allowing companies to run locally, however, would need to buy equipment, build structure to scale and buy a license or use an open-source model. A model like LLaMA is available to be used, requiring computational power to run the model.
+Models are just the Neural Network, with the parameters, weights, and others. Allowing companies to run locally, however, would need to buy equipment, build a structure to scale and buy a license or use an open-source model. A model like LLaMA is available to be used, requiring computational power to run the model.
 
 ## How to test and iterate with different models to understand performance on Azure
 
@@ -116,7 +116,7 @@ Most of the models we mentioned in previous paragraphs (OpenAI models, open sour
 
 ![Model catalog](./images/AzureAIStudioModelCatalog.png?WT.mc_id=academic-105485-koreyst)
 
-- Review the model card, including a detailed description of intended use and training data, code samples and evaluation results on internal evaluations library.
+- Review the model card, including a detailed description of intended use and training data, code samples and evaluation results on the internal evaluations library.
 
 ![Model card](./images/ModelCard.png?WT.mc_id=academic-105485-koreyst)
 
@@ -147,7 +147,7 @@ There are several approaches a business can use to get the results they need fro
 
 - **Retrieval Augmented Generation, RAG**. Your data might exist in a database or web endpoint for example, to ensure this data, or a subset of it, is included at the time of prompting, you can fetch the relevant data and make that part of the user's prompt.
 
-- **Fine-tuned model**. Here, you trained the model further on your own data which leads to the model being more exact and responsive to your needs but might be costly.
+- **Fine-tuned model**. Here, you trained the model further on your own data which led to the model being more exact and responsive to your needs but might be costly.
 
 ![LLMs deployment](./images/Deploy.png?WT.mc_id=academic-105485-koreyst)