# Creative Writing Enhancement

The final iteration of the Magnum series based on Llama-3.3-70B-Instruct, merging multiple rsLoRA fine-tuned versions to simulate the writing style and quality of Claude 3 Sonnet/Opus series models.

A pre-trained language model that integrates multiple 70B-parameter-scale models, based on the 'Forgotten Safe Word' foundation model, featuring an unrestrained style and a tendency for novel/story writing.

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

GodSlayer-12B-ABYSS is a 12B-parameter model obtained by merging multiple pre-trained language models through mergekit, designed to reduce positivity bias while maintaining stability and coherence, and to enhance realism and diversified response capabilities.

32-bit floating-point upgraded large language model, significantly improving text generation quality and quantization performance through full-component FP32 remastering

A creative writing-enhanced model fine-tuned on DeepSeek-R1-Distill-Qwen-14B, with significant improvements in creative writing capabilities

A creative writing enhancement model fine-tuned and optimized based on DeepSeek-R1-Distill-Qwen-14B, showing significant improvements in creative writing

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

A thought-oriented model fine-tuned based on Meta's Llama 3.3-70B-Instruct, focusing on enhancing creative writing and role-playing capabilities

This is a 9B-parameter language model merged using the mergekit tool, combining three models of different styles based on the TIES method

Archaeo-12B is a 12B-parameter large language model specifically designed for role-playing and creative writing, obtained by merging the Rei-12B and Francois-Huali-12B models

An 8X3B Mixture of Experts model with 4/8 experts activated, each equipped with reasoning techniques. Total parameters are 24B, but the actual model size is only 18.4B. Suitable for both creative and non-creative use cases as well as general purposes.

A fusion model specifically designed for role-playing and creative writing, combining Rei-12B and Francois-Huali-12B via Slerp algorithm

This is a 12B-parameter language model merged using the mergekit tool, specializing in creative writing and role-playing tasks with a unique narrative style.

Slush is a two-stage model trained with high LoRA dropout rate, focusing on enhancing creativity and role-playing capabilities

A specialized model focused on role-playing/story writing, based on Qwen2.5-14B with full-parameter fine-tuning, incorporating synthetic and natural data.

A specialized model focused on role-playing/story writing, fully fine-tuned based on Qwen2.5-32B, integrating synthetic and natural data.

A creative writing model based on the Mistral architecture, renowned for its exaggerated style and unpredictable creative output, specifically designed for prose, fiction writing, and role-playing.

NemoMix-Unleashed-12B is a 12B-parameter language model based on the MistralAI architecture, created by merging multiple high-quality models using the mergekit tool. It is particularly well-suited for roleplay and story creation.

A fully remastered 32k context large language model based on TeeZee/DarkSapling-7B-v1.1, excelling in instruction following, reasoning depth, and emotional expression

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

Based on the Mistral 7B large language model, fine-tuned through pre-trained model merging on the Date-DPO-v2 dataset, excelling in role-playing, creative writing, and general intelligent tasks.

A 70B-parameter large language model merged using the DARE linear fusion method, optimized for role-playing and story creation

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.

Psyfighter2 is a fusion model created by the KoboldAI community, enhanced with medical data to improve fictional capabilities, but not suitable for actual medical use.

The TIE Fighter is a hybrid model achieved by merging two different LoRAs, excelling in creative generation and supporting various application scenarios such as story creation, character dialogue, and adventure games.