Content
@
0 reply
0 recast
0 reaction
ππͺπΎπ‘π‘πΎ
@gm8xx8
Reaching 1B Context Length With RAG Zyphra: https://www.zyphra.com/post/reaching-1b-context-length-with-rag retrieval system enables LLMs to process up to 1 billion tokens efficiently on a standard CPU using a sparse graph-based approach. Outperforms RAG methods with dense embeddings or long-context transformers. Iβm impressed with the work Zyphra has been doing in the SSM space (most recently Zamba2-7B) so Iβm eager to see more.
6 replies
5 recasts
21 reactions
osama
@osama
highlights *standard cpu* wat?
0 reply
0 recast
1 reaction
Kazi
@kazi
for real?
0 reply
0 recast
1 reaction
wizard not parzival
@shoni.eth
i want the cross-knowledge of not using rag though, am i a moron be honest
0 reply
0 recast
0 reaction
daivd π©π½ β
@qt
1B is a lotta lotta LOTTA tokens, thousands of books. Very exciting
0 reply
0 recast
0 reaction
manansh βοΈ
@manansh
1 billion is outrageous
0 reply
0 recast
0 reaction
Jake Casey
@jakeacasey
I'm not super booked up-- does this mean that somebody built a retrieval system that works fine with 1 billion tokens on normal hardware?
0 reply
0 recast
0 reaction