Merge pull request #821 from sergiopaniego/unit-12-discord

Updated Discord links and nits in Chapter 12

Author: sergiopaniego

chapters/en/chapter12/1.mdx

@@ -12,9 +12,9 @@ LLMs have shown excellent performance on many generative tasks. However, up unti
 
 Open R1 is a project that aims to make LLMs reason on complex problems. It does this by using reinforcement learning to encourage LLMs to 'think' and reason. 
 
-In simple terms, the model is train to generate thoughts as well as outputs, and to structure these thoughts and outputs so that they can be handled separately by the user. 
+In simple terms, the model is trained to generate thoughts as well as outputs, and to structure these thoughts and outputs so that they can be handled separately by the user. 
 
-Let's take a look at an example. We gave ourself the task of solving the following problem, we might think like this:
+Let's take a look at an example. As we gave ourself the task of solving the following problem, we might think like this:
 
 ```sh
 Problem: "I have 3 apples and 2 oranges. How many pieces of fruit do I have in total?"
@@ -86,7 +86,7 @@ If you don't have all the prerequisites, check out this [course](/course/chapter
 ## How to Use This Chapter
 
 1. **Read Sequentially**: The sections build on each other, so it's best to read them in order
-2. **Share Notes**: Write down key concepts and questions and discuss them with in the community in [Discord](https://discord.gg/F3vZujJH)
+2. **Share Notes**: Write down key concepts and questions and discuss them within the community in [Discord](https://discord.gg/UrrTSsSyjb)
 3. **Try the Code**: When we get to practical examples, try them yourself
 4. **Join the Community**: Use the resources we provide to connect with other learners
 

chapters/en/chapter12/6.mdx

@@ -10,7 +10,6 @@ In this exercise, you'll fine-tune a model with GRPO (Group Relative Policy Opti
 
 Unsloth is a library that accelerates LLM fine-tuning, making it possible to train models faster and with less computational resources. Unsloth is plugs into TRL, so we'll build on what we learned in the previous sections, and adapt it for Unsloth specifics.
 
-
 <Tip>
 
 This exercise can be run on a free Google Colab T4 GPU. For the best experience, follow along with the notebook linked above and try it out yourself.