Update README.md

README.md

@@ -12,7 +12,7 @@ The importance matrix was trained for 100K tokens (200 batches of 512 tokens) us
 * Using Q8 K-cache (instead of F16) you can fit up to 43-44K context but inference speed goes down a little bit.
 * Also for some reason I need to use 1.0 penalty to avoid the response being cut-off.
 
-Prompt template (ends with a space after `ASSISTANT:`)
+Prompt template:
 ```
 You are a helpful assistant. USER: {context} {question} Don't give information outside the document or repeat your findings. Keep your response short and direct. ASSISTANT:
 ```