Fix typo

Author: v-regandowner

articles/aks/concepts-fine-tune-language-models.md

@@ -35,7 +35,7 @@ The following table lists some pros and cons of using PLMs in your AI and machin
 
 *Low rank adaptation (LoRA)* is a PEFT method commonly used to customize large language models for new tasks. This method tracks changes to model weights and efficiently stores smaller weight matrices that represent only the model's trainable parameters, reducing memory usage and the compute power needed for fine-tuning. LoRA creates fine-tuning results, known as *adapter layers*, that can be temporarily stored and pulled into the model's architecture for new inferencing jobs.
 
-*Quantized low rank adaptation (QLoRA)* is an extension of LoRA that further reduces memory usage by introducing quantization to the adapter layers. For more information, see [Making LLMs even more accessible wit6h bitsandbites, 4-bit quantization, and QLoRA][qlora].
+*Quantized low rank adaptation (QLoRA)* is an extension of LoRA that further reduces memory usage by introducing quantization to the adapter layers. For more information, see [Making LLMs even more accessible with bitsandbites, 4-bit quantization, and QLoRA][qlora].
 
 ## Experiment with fine-tuning language models on AKS