Your NameandClaude Opus 5 3b1de05760 litellm: add local_qwen2.5-14b, the structured-output tier ...

paperless-ai needs a model that holds strict JSON without being asked,
because it does not send response_format. llama3.1:8b breaks the shape
and qwen2.5:72b cannot answer inside its client timeout. 14B clears both.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>

2026-09-12 20:18:29 -04:00

..

main.yml

litellm: add local_qwen2.5-14b, the structured-output tier

2026-09-12 20:18:29 -04:00

vault.yml

litellm: pull /meridian secrets in-playbook from Infisical (runner-agnostic)

2026-06-05 13:00:54 -04:00