Awesome!

#6
by SicariusSicariiStuff - opened

Awesome to see DeepseekV3 architecture on a model we can all run, thank you!

Are there any plans to make a longer context model?

I agree @SicariusSicariiStuff we have been waiting for a moe in this size range, would like to see more context length as well.

are you guys running with RoPE enabled?

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment