mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-22 06:43:57 +00:00
This also makes it easier to truncate long inputs the same as shifting but does not actually implement it. This type of truncation has a trade off between quality and time to first token.
6.5 KiB
6.5 KiB