@voooooogel Might be interesting to see how r1-zero compares. In SpeechMap it's a very different model, presumably due to no additional helpful/harmless/etc steering phase.
in reply to: 1920789986607280549
cited on: deepseek-r1-zero
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.