가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

elie
@eliebakouch
training llm @PrimeIntellect (prev: @huggingface) anon feedback:
가입 January 2024
4.5K 팔로잉 중    22.7K
we replicated anthropic jspace analysis on @thinkymachines Inkling new 1T model! it seems to be an outlier: where other models split into near-orthogonal sensory/workspace/motor blocks, inkling keeps roughly one geometry across the whole stack (early-late CKA ~0.8 vs ~0.5 elsewhere) we also look computed the J-space of @poolsideai's laguna XS 2.1 in bf16 vs nvfp4 to test the impact of quantization. result: almost none. the quantized model has the same jlens space as the non-quantized one both jspace checkpoint are up on hugging face!
더 보기
0
40
1.2K
106
커뮤니티로 전달