Viewing profile — rosmine

My first advice is to have a test set with clear improvement, and a clear "wow" demo use case. There are lots of "breakthroughs" that seem good but aren't (e.g. some new architectu…

I agree :) Also, I heard Teknium trained the original Hermes model on 2x 4090. You can do a lot with a little compute

Yes! It scared me too. I tried to insure it under my renter's insurance policy, but they not surprisingly refused. I had to get business insurance to cover it

Hi! Thank you so much for posting this! I got back luck/timing when I tried, so happy it made it to the front page! (I am the author)

Standard LLM training is surprisingly bad at making the model outputs match the training data distribution, so the writing quality is bad. I made a new training algorithm called Di…