Disappointed to note that the 8k context length is far short of Mixtral 8x22B's ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

loudmax on April 18, 2024 | parent | context | favorite | on: Meta Llama 3

Disappointed to note that the 8k context length is far short of Mixtral 8x22B's 64k context length.

Still, the published performance metrics are impressive. Kudos to Meta for putting these models out there.

rising-sky on April 18, 2024 [–]

They’re going to increase the context window

https://www.threads.net/@zuck/post/C56MOZ3xdHI/?xmt=AQGzjzaz...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact