Post
916
We're excited to release BananaMind 2 SLMoE, an experimental sequence-level mixture-of-experts model.
It uses only 8M parameters per message but has 25M total parameters, 13 experts (out of 64) are selected based on the message prefix and reused for the entire response.
We're testing with this sequence-level architecture to find out how big the capability loss actually is and how much of it can be fixed.
The long-term idea is that this could make very large sparse models usable on machines that can't fit them in RAM by putting the entire model (which is big) on disk and only loading the active parts into VRAM.
This architecture is still in research and shouldn't be used for production models.
We trained it on 60B tokens (of FineWeb-HQ, FineWeb-Edu, DCLM ,Cosmopedia v2, FineMath and NPSet-2) on 8 RTX Pro 6000s.
Check it out at BananaMind/BananaMind-2-SLMoE
Follow us for future models:
BananaMind
@vovaRL
@Banaxi-Tech
@DedeProGames
BananaMind 2 Pro in a few days. You've been waiting 22 days for it.
It uses only 8M parameters per message but has 25M total parameters, 13 experts (out of 64) are selected based on the message prefix and reused for the entire response.
We're testing with this sequence-level architecture to find out how big the capability loss actually is and how much of it can be fixed.
The long-term idea is that this could make very large sparse models usable on machines that can't fit them in RAM by putting the entire model (which is big) on disk and only loading the active parts into VRAM.
This architecture is still in research and shouldn't be used for production models.
We trained it on 60B tokens (of FineWeb-HQ, FineWeb-Edu, DCLM ,Cosmopedia v2, FineMath and NPSet-2) on 8 RTX Pro 6000s.
Check it out at BananaMind/BananaMind-2-SLMoE
Follow us for future models:
@vovaRL
@Banaxi-Tech
@DedeProGames
BananaMind 2 Pro in a few days. You've been waiting 22 days for it.
