@dlbydq @aidan_mclau are you imagining replicating claude-like training on an open source model?
same thread: 1956458735909704085 1956459085131645111 1956459646572794144 1956460016006988153 1956470964780417473 1956475514220425282 1956475770483966117 1956477048425529724 1956478404087406772 1972168380460498986
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.