Feedback.
#6
by
Pankaj8922
- opened
As you guys described,
That model will switch its mode on the basis of previous prompts.
You guys could teach model instead, if it needed to do COT or not.
Like Deepseek.
If you say "Hi"
It's says:"
<|think|> <|think|> Hello, How can I assist you today."
So here model basically skip the reasoning part as it knew that"Hi" isn't a question to think about.
I hope this will be valuable in any manner.