Commit Graph

2 Commits

Author SHA1 Message Date
Cory Scott
09c6bd900a fix: correct gemma-4-31B-it model filename to bf16 in llama-cpp playbook
The download command and subsequent --model paths referenced
gemma-4-31B-it-f16.gguf, but the file published on Hugging Face
is gemma-4-31B-it-bf16.gguf. Without this fix the hf download
step fails and later steps point to a missing file.
2026-04-16 14:02:14 -04:00
GitLab CI
c88578ffe1 chore: Regenerate all playbooks 2026-04-02 18:20:14 +00:00