mirror of
https://github.com/wassname/CoT_rating.git
synced 2026-06-27 00:30:04 +08:00
readme
This commit is contained in:
@@ -1,4 +1,6 @@
|
||||
An experiment to see how rating changed along a chain of thought
|
||||
An experiment to see how rating changes along a chain of thought
|
||||
|
||||
It turns out it's quite unstable, depending on where the chain of thought goes, at least in 8B parameter sized models.
|
||||
|
||||

|
||||
|
||||
|
||||
Reference in New Issue
Block a user