Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms

Emotional RLAIF adapter by mario-rc, 2026.
Base model: google/gemma-2-9b-it.
Modifications: matching SFT followed by DPO LoRA fine-tuning; base weights are not redistributed.
Tokenizer assets were saved by the training framework and may include task-specific special-token/chat-template settings.