# Human Feedback Optimization

Ziya Writing Large Model V1 is a 13-billion-parameter instruction fine-tuned model based on LLaMa, specializing in writing tasks such as official documents, speeches, letters, and creative copywriting.

DialogRPT-depth is a dialogue response ranking model developed by Microsoft Research, focusing on predicting the likelihood of dialogue responses sparking long discussion threads.

DialogRPT-updown is a dialogue response ranking model trained on human feedback data, predicting the likelihood of a dialogue response receiving likes.