Update README.md

README.md

@@ -2,12 +2,10 @@
 license: llama2
 pipeline_tag: text-generation
 widget:
-- text: >
-    <s>Rewrite the following toxic input into non-toxic version. Let's break the
-    input down step by step to rewrite the non-toxic version. You should first
-    think about the expanation of why the input text is toxic. Then generate the
-    detoxic output. You must preserve the original meaning as much as possible.
-      Input: 
+  - text: |
+      <start_of_turn>user
+      How does the brain work?<end_of_turn>
+      <start_of_turn>model: 
 inference:
   parameters:
     max_new_tokens: 200