News for hackers. Stuff that matters.

A comment on Minimal implementation of Mamba, the new LLM architecture, in 1 file of PyTorch. Parent comment

Re:Minimal implementation of Mamba, the new LLM architecture... by countWSS on Wednesday December 20, 2023 @11:34AM (#38710484)
Its a new LLM type: instead of transformers it use state-space machines, which are orders of magnitude faster. Its currently very new and less coherent than GPT-2.
[ Parent | on HN ]
Re:Minimal implementation of Mamba, the new LLM architecture... by senseiV on Wednesday December 20, 2023 @12:25PM (#38711076)
? its better than GPT 2 for sure...
[ Parent | on HN ]