Bamba: An open-source LLM that crosses a transformer with an SSM

research.ibm.com Meet Bamba, IBM’s new attention-state space model

The open-source LLM combines the sequence-modeling skill of a transformer with the inferencing speed of an SSM. IBM Granite will soon adopt key Bamba features.

Comments

Artificial Intelligence @lemmy.world cm0002 @lemmy.world 2w ago

Meet Bamba, IBM’s new attention-state space model

research.ibm.com /blog/bamba-ssm-transformer-model

0 comments