is it fine tuned for reasoning?
#1
by
wichofer
- opened
I cannot find documentation or details for this model, so my question is, based on it's name, can I assume it is a mistral-7b fine-tuned for reasoning with ReAct prompting?
I'm looking into this because the estandard mistral-7b works very bad for my react use case so i'm looking for alternatives.
Hi,
it was trained for a special use case that uses ReAct prompting.... Thus, I don't think, that this model is usefull for you in any way...