Files
LocalAI/gallery
Ettore Di Giacinto d252908b2f fix(gallery): use tokenizer templates for Gemma
Let the model-provided tokenizer template format Gemma conversations instead of maintaining a shared inline prompt template.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-07-29 14:02:20 +00:00
..
2026-04-08 19:23:16 +02:00
2025-08-06 10:40:46 +02:00
2026-04-19 21:31:22 +00:00