Fix TRL SFT notebook link (path moved in huggingface/trl#6820)

app/src/content/chapters/sft.mdx

@@ -15,7 +15,7 @@ In this tutorial, we'll fine-tune the NanoChat model using pure PyTorch, giving
 
 <Note>
 
-**Want a production-ready solution?** TRL is Hugging Face's reinforcement learning library with battle-tested SFT implementations. Check out the [SFT notebook](https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb) to use it with your nanochat checkpoint.
+**Want a production-ready solution?** TRL is Hugging Face's reinforcement learning library with battle-tested SFT implementations. Check out the [SFT notebook](https://github.com/huggingface/trl/blob/main/examples/sft_qlora/sft_qlora.ipynb) to use it with your nanochat checkpoint.
 
 </Note>
 
@@ -397,7 +397,7 @@ step=00050 | loss=1.8029 | lr=6.67e-06
 
 <Sidenote>
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb)  
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://github.com/huggingface/trl/blob/main/examples/sft_qlora/sft_qlora.ipynb)  
 
 </Sidenote>