Update procedure/tips_and_tricks_for_training_with_qlora_on_cheap_desktop_PC.md

procedure/tips_and_tricks_for_training_with_qlora_on_cheap_desktop_PC.md

@@ -5,9 +5,9 @@ https://rentry.org/cpu-lora
 https://github.com/ggerganov/llama.cpp/pull/2632
 
 Making your own fine-tune requires a few things to be in place before you start
-1. you need a model that you want to use as a base
-2. you need to get a dataset that will be used to communicate to the model the things you expect it to do
-3. you need to have access to hardware that you will use for training and a training method that will work on this hardware.
+- you need a model that you want to use as a base
+- you need to get a dataset that will be used to communicate to the model the things you expect it to do
+- you need to have access to hardware that you will use for training and a training method that will work on this hardware.
 
 1.
 For the model, I know I wanted to go with llama 2 7B model or something that would be based on that to have reasonable coherency and small size.