logo
Sign In
grayxu
@grayxu
·
a year ago
·
a year ago
function
Hybrid_Thinking_Pipe
Last Updated
a year ago
Created
a year ago
Function
pipe
v0.3.1
Name
Hybrid_Thinking_Pipe
Downloads
192+
Saves
0+
Description
You can use DeepSeek R1 or QwQ 32B for cheap and fast thinking, and use stronger and more expensive models like Claude 3.7 Sonnet for final summarization output, to achieve a better balance between inference cost and performance.

You can set two booleans, REASONING_CONTENT_AS_CONTEXT and CONTENT_AS_CONTEXT, to control whether the reasoning and actual output are passed as context to the output model:

  • The default behavior is consistent with Deep Claude, where only the reasoning content is used as context. However, be aware that this might confuse the output model.
  • In practice, Aider only uses the final output of the reasoning model as context for the output model. If you want the same approach, set REASONING_CONTENT_AS_CONTEXT=False and CONTENT_AS_CONTEXT=True.
0