appvoid

Yes, I got the script for ArithMark-3 and I can re-run it with no issues.

Mostly across harness details rather than a completed five-seed sweep. We have checked the checkpoint under repeated runs and small evaluation-pipeline variations, but I do not want to represent that as a formal variance estimate.

Your distinction is valid though, prompt formatting and answer parsing measure harness sensitivity, while multiple seeds under one frozen configuration might establish the actual noise band. I don't know if it will be published at all. Since is a little bit chaotic keeping base skills while improving them so our iteration method is barely reproducible.

That’s a fair point. At this scale, instruction tuning is definitely a capacity tradeoff rather than a free capability layer, so preserving the base model’s strengths will be one of the main acceptance criteria.

Regarding the post-merge result, we have done additional validation runs and the performance appears directionally consistent, although I would prefer to publish the full repeated-evaluation results once the methodology and comparison conditions are finalized. At 90M, even small evaluation details can meaningfully affect the reported ranking.

The instruct version will be treated as a separate checkpoint rather than a replacement for the base model.

Can't wait to see what the community 🪐do with this! 🚀🚀🚀

Cool stuff right there! Keep it up

because its my own and im currently training it

you should do more of that magic you did with hellaswag on BananaMind-2-Medium

BananaMind 2 pro... ok i know

Let's Go!!!

One is Kimi-K3, which I have heard of briefly. What's the other one? I hope it's a video generation model

You guessed right! One of them is the best biggest model. The other one is the best smallest.

Following

Hey

following