(arxiv.org)

34 points dpstart01 | 2 comments | 15 Apr 25 17:00 UTC | HN request time: 0.445s | source

1. solomatov ◴[15 Apr 25 19:47 UTC] No.43697542[source]▶

Does anyone know if there were any attempts to test Mamba on really large scale? To me this model looks as the most promising successor to the transformer architecture. Does anyone know why it might not be the case or what are other alternatives?

replies(1): >>43700621 #

2. tangjurine ◴[16 Apr 25 01:59 UTC] No.43700621[source]▶

>>43697542 (TP) #

Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ultra-Large Model: https://news.ycombinator.com/item?id=43447254

↑

M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models