Skip to content

0.9.23 - additional llama:8b quantizations
Compare
Choose a tag to compare
@lukemarsden lukemarsden released this 16 Jul 11:23
· 473 commits to main since this release
0.9.23
5b0bfb8
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.

What's Changed

Adds support for llama3:8b-instruct-fp16, llama3:8b-instruct-q6_K and llama3:8b-instruct-q8_0 through the API and app configuration yaml. Models must be added to RUNTIME_OLLAMA_WARMUP_MODELS env var on the runner before they will work.

Full Changelog: 0.9.22...0.9.23

Contributors

lukemarsden
Assets 2