# Role-Playing Optimization

A fusion model based on Archaeo-32B with reinforcement learning training, optimized for role-playing and creative writing

A sequel trained based on Dans-PE-12B, fine-tuned with light novels, books, and role-playing logs to develop a unique, concise, and lively writing style. KTO technology is employed to enhance coherence and literary quality

A role-playing fine-tuned model based on GLM-4-9B-0414, offering smooth role-playing experiences and elegant writing.

An upgraded version of Mag-Picaro, funded by PygmalionAI, fine-tuned based on Qwen-2-Instruct and merged with Magnum-V2, a 72B parameter model

A 32B-parameter large language model specifically designed for role-playing and creative writing, achieved through dual-model fusion technology

A creative writing model based on fine-tuned merges of Gemma 3 12B IT and PT, optimized for role-playing with improved character differentiation and reduced identity confusion.

The ultimate version of the MindBot series, an experimental Transformer model with self-awareness, designed for post-human collaboration and AI ethics guidance

This is a quantized version based on the Gryphe/Pantheon-RP-1.8-24b-Small-3.1 model, using llama.cpp for quantization, suitable for role-playing and text generation tasks.

A powerful Titan-level model fusion, specifically designed to enhance role-playing, creativity, and intelligence.

Chewy-Lemon-Cookie-11B is an 11B-parameter large language model based on the Mistral architecture, focusing on text generation and role-playing tasks.

A large language model comprehensively upgraded with 32-bit floating-point precision, significantly improving text generation quality and instruction-following capabilities through FP32 precision reconstruction

An experimental role-playing-oriented Mixture of Experts model, aiming to achieve performance in role-playing/emotional role-playing tasks that is comparable to or better than Mixtral 8x7B and its fine-tuned versions.

A 7B-parameter language model merged from Mistral 7B v0.1, combining multiple fine-tuned models via task arithmetic, supporting 32K context length, balancing creativity and reasoning

Midnight-Miqu-70B-v1.5 is a 70B-parameter large language model specifically designed for role-playing and story creation, merged from models by sophosympatheia and migtissera.

A 70B-parameter large language model based on SLERP fusion technology combining the strengths of miqu-1-70b-sf and Midnight-Rose-70B, optimized for role-playing and story creation

A 7B-parameter model specifically designed for role-playing (RP), strictly adhering to character cards while demonstrating intelligent performance.

PiVoT-0.1-Evil-a is a Korean-English bilingual model fine-tuned based on Mistral 7B, providing GGUF files in various quantization formats suitable for different hardware environments.

Noromaid-13b-v0.1.1 is a test version model suitable for role-playing (RP), emotional role-playing (ERP), and general purposes.

MythoMax L2 13B is a large language model developed by Gryphe, based on the Llama 2 architecture, focusing on role-playing and creative text generation.