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.
51 Pulls Updated 3 months ago
2490e7468436 · 65B
{
"stop": [
"<start_of_turn>",
"<end_of_turn>"
]
}