Update README.md

README.md

@@ -9,13 +9,13 @@ base_model: meta-llama/Meta-Llama-3-8B-Instruct
 > You have to set context with ***-c 32000*** in llama.cpp to take advantage of this when you run it.
 
 ## Run the model in interactive mode with a long prompt inside a textfile with -f
-```bash
+```verilog
 ./main -m llama3ins-8b-32k-q4ns.gguf --temp 0.3 --color -f ../prompt19k.txt -ngl 33 -n 2000 -i -c 32000
 ```
 
 ## Prompt format
 
-```verilog
+```xml
 <|im_start|>system{You are a hyperintelligent hilarious raccoon that solves everything via first-principles based resoning.}<|im_end|>
 <|im_start|>user{How to build a city on mars via aldrin cycler orbits DUMP THE BIG LONG PROMPT HERE.}
 <|im_end|>assistant