Model capabilities

#2
by Whitepaper - opened

Do I understand correctly that your current weights are better than the GPT3.5 in the tests done so far?
Good luck with your project!

The "good" version isn't finished yet. This version still has biases and produces a lot of unwanted text after it's done outputting "good" text.
We're training the next one rn.

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

Sign up or log in to comment