From f3016aea58fcc80555ee872daeda53e87e78202b Mon Sep 17 00:00:00 2001 From: maximevoisincohere <157384859+maximevoisincohere@users.noreply.github.com> Date: Sun, 25 Aug 2024 22:20:51 +0200 Subject: [PATCH] Update prompting-command-r.mdx Signed-off-by: maximevoisincohere <157384859+maximevoisincohere@users.noreply.github.com> --- .../prompt-engineering/prompting-command-r.mdx | 14 +------------- 1 file changed, 1 insertion(+), 13 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 index 86d429fe..859d640b 100644 --- a/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx +++ b/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx @@ -55,19 +55,7 @@ This way, RAG and Summarization follow a similar prompt template. It is the Augm >
>
> ## Style Guide -> \{STYLE_GUIDE} ->\<|END_OF_TURN_TOKEN|> ->\{CHAT_HISTORY} ->\<|START_OF_TURN_TOKEN|> ->\<|SYSTEM_TOKEN|> ->\{RETRIEVED_SNIPPETS_FOR_RAG or TEXT_TO_SUMMARIZE} ->\<|END_OF_TURN_TOKEN|> ->\<|START_OF_TURN_TOKEN|> ->\<|SYSTEM_TOKEN|> ->\{INSTRUCTIONS} ->\<|END_OF_TURN_TOKEN|> ->\<|START_OF_TURN_TOKEN|> ->\<|CHATBOT_TOKEN|>""" +> \{STYLE_GUIDE}\<|END_OF_TURN_TOKEN|>\{CHAT_HISTORY}\<|START_OF_TURN_TOKEN|>\<|SYSTEM_TOKEN|>\{RETRIEVED_SNIPPETS_FOR_RAG or TEXT_TO_SUMMARIZE}\<|END_OF_TURN_TOKEN|>\<|START_OF_TURN_TOKEN|>\<|SYSTEM_TOKEN|>\{INSTRUCTIONS}\<|END_OF_TURN_TOKEN|>\<|START_OF_TURN_TOKEN|>\<|CHATBOT_TOKEN|>""" We can see that the prompt is set up in a structured way where we have sections for things like the basic rules we want the model to follow, the task we want it to solve, and the style in which it should write its output in.