# Role-play optimization

QwQ-32B-ArliAI-RpR-v4 is a high-performance role-play and creative writing model developed by ArliAI, fine-tuned based on QwQ-32B, with a focus on reducing repetition and enhancing creative output.

A merged model based on Llama 3 70B architecture, optimized for story generation and role-play, supporting long context windows

An intermediate model during the Tantum merging process, created by merging multiple 24B-parameter Mistral and Llama3 variants, suitable for role-playing and text generation tasks.

A hybrid model based on multiple 12B parameter models, specializing in Russian and English role-playing and text generation

Daring Maid-20B-V1.1 is an upgraded version based on DaringMaid-20B, with the main update being the replacement of Noromaid-13b from v0.1.1 to v0.3, along with a slight increase in Noromaid's weight to ensure better compatibility.

orthogonal-2x7B-v2-base is a Mixture of Experts model based on Mistral-7B-Instruct-v0.2 and SanjiWatsuki/Kunoichi-DPO-v2-7B, specializing in text generation tasks.

Sonya-7B is a 7B-parameter large language model that excels in the MT-Bench benchmark, surpassing GPT-4 in the first round and ranking second overall.

MythoLogic-L2-13B is an improved model based on Llama 2, focusing on enhancing role-playing capabilities and understanding complex instructions.