Update prompting-command-r.mdx

Signed-off-by: maximevoisincohere <[email protected]>
cohere-ai · Aug 25, 2024 · 050c92d · 050c92d
1 parent 8c867ac
commit 050c92d
Showing 1 changed file with 12 additions and 12 deletions.
diff --git a/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx b/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx
@@ -56,18 +56,18 @@ This way, RAG and Summarization follow a similar prompt template. It is the Augm
 > <br />
 > <span class="dark-sangria-text">## Style Guide</span>  
 > <span class="dark-sangria-text">\{STYLE_GUIDE}</span>
-> <span class="brown-text">\<|END_OF_TURN_TOKEN|></span>
-> <span class="orange-text">\{CHAT_HISTORY}</span>
-> <span class="brown-text">\<|START_OF_TURN_TOKEN|></span>
-> <span class="dark-orange-text">\<|SYSTEM_TOKEN|></span>
-> <span class="orange-text">\{RETRIEVED_SNIPPETS_FOR_RAG or TEXT_TO_SUMMARIZE}</span>
-> <span class="brown-text">\<|END_OF_TURN_TOKEN|></span>
-> <span class="brown-text">\<|START_OF_TURN_TOKEN|></span>
-> <span class="dark-orange-text">\<|SYSTEM_TOKEN|></span>
-> <span class="orange-text">\{INSTRUCTIONS}</span>
-> <span class="brown-text">\<|END_OF_TURN_TOKEN|></span>
-> <span class="brown-text">\<|START_OF_TURN_TOKEN|></span>
-> <span class="dark-orange-text">\<|CHATBOT_TOKEN|></span>"""
+><span class="brown-text">\<|END_OF_TURN_TOKEN|></span>
+><span class="orange-text">\{CHAT_HISTORY}</span>
+><span class="brown-text">\<|START_OF_TURN_TOKEN|></span>
+><span class="dark-orange-text">\<|SYSTEM_TOKEN|></span>
+><span class="orange-text">\{RETRIEVED_SNIPPETS_FOR_RAG or TEXT_TO_SUMMARIZE}</span>
+><span class="brown-text">\<|END_OF_TURN_TOKEN|></span>
+><span class="brown-text">\<|START_OF_TURN_TOKEN|></span>
+><span class="dark-orange-text">\<|SYSTEM_TOKEN|></span>
+><span class="orange-text">\{INSTRUCTIONS}</span>
+><span class="brown-text">\<|END_OF_TURN_TOKEN|></span>
+><span class="brown-text">\<|START_OF_TURN_TOKEN|></span>
+><span class="dark-orange-text">\<|CHATBOT_TOKEN|></span>"""
 
 
 We can see that the prompt is set up in a structured way where we have sections for things like the <span class="green-text">basic rules</span> we want the model to follow, the <span class="purple-text">task</span> we want it to solve, and the <span class="pink-text">style</span> in which it should write its output in.