Works fine being a test model!
#1
by
1NoobArtist
- opened
Hi,
Many thanks for creating this model. Works fine being a test model.
But this model is very adamant. It should be taught to answer next set of questions or respond as per the flow of the conversation. At present, this model seems to force its own wishes (as the character). It disregards the next set of commands/chat from the user.
Thanks!
I noticed the same thing. I'm hoping to fix it with the next iteration which is going to include a lot more multi-turn data and variety. I mostly wanted to do a quick test to make sure I could reasonably extend the context with rope, which did seem to work well.
will look forward to the next update!
1NoobArtist
changed discussion status to
closed
1NoobArtist
changed discussion status to
open