News for hackers. Stuff that matters.

A comment on StreamingLLM: tiny tweak to KV LRU improves long conversations. Parent comment

Re:StreamingLLM: tiny tweak to KV LRU improves long conversa... by kgeist on Tuesday February 13, 2024 @10:09AM (#39358282)
Here they simply used different models for different turns and apparently it gave more "engaging" results:

https://arxiv.org/abs/2401.02994

[ Parent | on HN ]

There are no comments on this comment yet.