Discussion about this post

User's avatar
Trelis Research's avatar

V nice write-up.

1. Why dyou think Nvidia trains Nemotron? To keep up capabilities? To offer a model that is "western frontier OSS"? [although includes distilling DeepSeek v4].

2. Why dyou think on policy student roll-outs are done rather than just direct distillation from the teacher. Does on-policy actually give better results (because it's on-policy), or, is it cheaper because you don't need to do a full decode on the teacher?

Thanks again.

2 more comments...

Ready for more?