The model is an instruction-tuned variant of rinna/gemma-2-baku-2b, utilizing Chat Vector and Odds Ratio Preference Optimization (ORPO) for fine-tuning. It adheres to the gemma-2 chat format.

2B

14 Pulls Updated 8 days ago

2490e7468436 · 65B
{ "stop": [ "<start_of_turn>", "<end_of_turn>" ] }