Merge pull request #5761 from msakande/peer-review-deepseek-tutorial

initial review of deep-seek-r1 tutorial

Author: denrea

articles/ai-foundry/foundry-models/includes/use-chat-reasoning/about-reasoning.md

@@ -9,14 +9,13 @@ author: santiagxf
 
 ## Reasoning models
 
-Reasoning models can reach higher levels of performance in domains like math, coding, science, strategy, and logistics. The way these models produce outputs is by explicitly using chain of thought to explore all possible paths before generating an answer. They verify their answers as they produce them which helps them to arrive to better more accurate conclusions. This means that reasoning models may require less context in prompting in order to produce effective results. 
+Reasoning models can reach higher levels of performance in domains like math, coding, science, strategy, and logistics. The way these models produce outputs is by explicitly using chain of thought to explore all possible paths before generating an answer. They verify their answers as they produce them, which helps to arrive at more accurate conclusions. As a result, reasoning models might require less context in prompting in order to produce effective results. 
 
-Such way of scaling model's performance is referred as *inference compute time* as it trades performance against higher latency and cost. It contrasts to other approaches that scale through *training compute time*. 
+This way of scaling a model's performance is referred to as *inference compute time* as it trades performance against higher latency and cost. In contrast, other approaches might scale through *training compute time*. 
 
-Reasoning models then produce two types of outputs:
+Reasoning models produce two types of content as outputs:
 
-> [!div class="checklist"]
-> * Reasoning completions
-> * Output completions
+* Reasoning completions
+* Output completions
 
-Both of these completions count towards content generated from the model and hence, towards the token limits and costs associated with the model. Some models may output the reasoning content, like `DeepSeek-R1`. Some others, like `o1`, only outputs the output piece of the completions.
+Both of these completions count towards content generated from the model. Therefore, they contribute to the token limits and costs associated with the model. Some models, like `DeepSeek-R1`, might respond with the reasoning content. Others, like `o1`, output only the completions.

articles/ai-foundry/foundry-models/includes/use-chat-reasoning/best-practices.md

@@ -14,8 +14,8 @@ When building prompts for reasoning models, take the following into consideratio
 > [!div class="checklist"]
 > * Use simple instructions and avoid using chain-of-thought techniques.
 > * Built-in reasoning capabilities make simple zero-shot prompts as effective as more complex methods. 
-> * When providing additional context or documents, like in RAG scenarios, including only the most relevant information may help preventing the model from over-complicating its response.
-> * Reasoning models may support the use of system messages. However, they may not follow them as strictly as other non-reasoning models.
-> * When creating multi-turn applications, consider only appending the final answer from the model, without it's reasoning content as explained at [Reasoning content](#reasoning-content) section.
+> * When providing additional context or documents, like in RAG scenarios, including only the most relevant information might help prevent the model from over-complicating its response.
+> * Reasoning models may support the use of system messages. However, they might not follow them as strictly as other non-reasoning models.
+> * When creating multi-turn applications, consider appending only the final answer from the model, without it's reasoning content, as explained in the [Reasoning content](#reasoning-content) section.
 
-Notice that reasoning models can take longer times to generate responses. They use long reasoning chains of thought that enabled deeper and more structured problem-solving. They also perform self-verification to cross-check its own answers and correct its own mistakes, showcasing emergent self-reflective behaviors.
+Notice that reasoning models can take longer times to generate responses. They use long reasoning chains of thought that enable deeper and more structured problem-solving. They also perform self-verification to cross-check their answers and correct their mistakes, thereby showcasing emergent self-reflective behaviors.