Naphula/Slimaki-Tavern-24B-v1.3

TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 30, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Naphula/Slimaki-Tavern-24B-v1.3 is a 24 billion parameter uncensored language model merge, created by Naphula using a two-stage multi_fusion method based on Mistral architecture. It is specifically designed and optimized for roleplay, creative writing, and storytelling, supporting vivid prose and conversational interactions. This model integrates components from DarkArtsForge/Morax-24B-v2, MuXodious/Maginum-Cydoms-24B-absolute-heresy, and Naphula/Slimaki-24B-v1.2, offering a 32768 token context length.

Loading preview...

Model Overview

Naphula/Slimaki-Tavern-24B-v1.3 is a 24 billion parameter uncensored language model, primarily developed for roleplay (RP), creative writing, and storytelling. It is a multi-stage merge of several pre-trained models, including DarkArtsForge/Morax-24B-v2, MuXodious/Maginum-Cydoms-24B-absolute-heresy, and Naphula/Slimaki-24B-v1.2, utilizing a custom multi_fusion method.

Key Capabilities

  • Uncensored Content Generation: Designed to produce narratives and roleplay content without typical censorship, including potentially violent or graphic erotic themes.
  • Specialized for Creative Tasks: Optimized for generating vivid prose, engaging in conversational roleplay, and creating diverse stories across genres like science fiction, horror, and romance.
  • Advanced Merging Technique: Employs a two-stage multi_fusion merge method, an extension of arcee_fusion, which incorporates alternate importance metrics like delta_mag and cosine_sim for enhanced parameter integration.
  • Multilingual Support: Supports a wide array of languages including English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Russian, and Korean.

When to Use This Model

  • Roleplay and ERP: Ideal for users seeking an uncensored model for immersive roleplay and erotic roleplay scenarios.
  • Creative Writing: Excellent for generating detailed stories, character dialogues, and descriptive prose.
  • Experimental Merging: Developers interested in exploring advanced model merging techniques and their impact on specific generation styles may find the multi_fusion method and its configurable importance metrics valuable.

Finetunes
2 models