# Role-playing optimization

A large language model with 24B parameters based on the Mistral architecture, optimized for role-playing and creative writing, using the GGUF quantization format

A multilingual, multi-purpose large language model supporting various professional domains and general tasks, suitable for role-playing, story creation, programming, and other scenarios.

This is the floating-point 16-bit version of Gryphe's MythoMax-L2-13B model converted to GGUF, designed for full-quality local inference on high-video-memory GPUs.

An optimized role-playing and story creation model that fixes the EOS token issue, reduces redundant output, and can use emojis.

Based on the fusion of multiple pre-trained language models, version V.5 has improved stability and content performance

Llamacpp imatrix quantized version based on PocketDoc/Dans-SakuraKaze-V1.0.0-12b, supporting multiple quantization types, suitable for text generation tasks.

A large language model fine-tuned based on Mistral-Nemo-Instruct, designed to replicate the exquisite prose quality of Claude 3 models

A high-performance language model optimized from the Qwen2.5-32B series, excelling in role-playing and creative writing

Thespis-Llama-3.1-8B is a language model fine-tuned based on a specific optimization method, designed for role-playing, creative writing, and interactive story-telling scenarios, which can enhance the realism and depth of character interactions.

Genetic Lemonade Unleashed is a large language model with 70B parameters designed specifically for role-playing (RP) and creative writing. It achieves a balance in writing style, creativity, and intelligence level by fusing multiple excellent models.

An instruction-following model fine-tuned based on Mistral-7B-V0.3, optimized for role-playing and story creation

A language model fine-tuned based on Llama-3.1-8B-Instruct, supporting personal freedom and decentralization philosophy as an unrestrained AI assistant

A 12B-parameter language model based on the SLERP fusion method, combining the strengths of Mag-Mell and UnslopNemo models, suitable for creative writing and role-playing scenarios

This is a new model obtained by merging multiple base models, optimized for role-playing scenarios and using the ChatML instruction format.

Mistral-NeMo-Minitron-8B-Instruct is a text generation model developed by NVIDIA, supporting various tasks such as role-playing, retrieval-augmented generation, and function calls, with the characteristics of high efficiency and accuracy.

A powerful text generation model based on Llama3, suitable for activities such as writing and role-playing, with high stability and low perplexity.

Two enhanced versions of the Command-R 35B model for horror themes, strengthened with the DARK HORROR NEO Imatrix dataset to enhance horror element generation

This is a Llama-3.1 model fine-tuned with DPO, which can behave more 'humanely' and avoid the rigid responses of AI assistants. It is suitable for role-playing scenarios.

A role-playing model based on the fusion of 36 models, created through 23 merging steps, combining creativity and intelligence.

A multi-model fusion solution based on Llama 3, balancing creativity and logic, suitable for role-playing and general tasks

A 32K long-context model optimized from Llama-3-8B, extending context length through PoSE training, specializing in role-playing and creative writing tasks

Jamet-8B-L3-MK.V-Blackroot is a role-playing and storytelling model based on Llama 3, optimized through multiple iterations and particularly suited for creative writing and interactive dialogues.

A model post-trained based on Meta-Llama-3-70B, specifically optimized for role-playing tasks while excelling in general domain instruction following and reasoning tasks.

A model for generating creative, brainstorming, role-playing, long stories, scenarios, and fictional content. It fuses multiple models in a unique way to generate highly creative and unpredictable text content.

This is a fusion model based on Mistral-7B-Instruct, combining DarkSapling's role-playing/story generation capabilities with some features of Bagel, utilizing Imatrix Plus compression technology to enhance quality