Update README.md

README.md

@@ -107,9 +107,9 @@ python example-chat.py ./model ./tokenizer/tokenizer.model 0.75 0.9 0 1.0 top_p
 
 # Run with top_k sampler, with temperature 0.7, with top_k value 40, default repetition penalty value
 python example-chat.py ./model ./tokenizer/tokenizer.model 0.7 0.0 40 1.17 top_k
-
-# of course, this is also applicable to a [python example.py] as well (see below)
 ```
+Of course, this is also applicable to a [python example.py] as well (https://github.com/randaller/llama-chat#typical-generation-with-prompt-not-a-chat)
+
 
 ### Enable multi-line answers