9
new qwen architecture? :o
(lemmy.blahaj.zone)
A community all about the Qwens! (LLMs, VLMs, WANs...)
Here their blog page and their free chat interface
Post are allowed to have any format.
It is advised to put "Qwen" into the title somewhere.
Afaik all LLMs have very derp recurrance, as that's what provides their context window size.
The more recurrant params they have, the more context window they can store.