Awesome!

by SicariusSicariiStuff - opened Feb 24

Feb 24

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

Are there any plans to make a longer context model?

Feb 26

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

6 days ago

are you guys running with RoPE enabled?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

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

· Sign up or log in to comment