N-Bot-Int/OpenElla-NovelWriter-Requiem

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 13, 2026License:agpl-3.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

N-Bot-Int/OpenElla-NovelWriter-Requiem is an 8 billion parameter Llama 3.1-based language model developed by N-Bot-Int, specifically fine-tuned for enhanced roleplay capabilities and creative writing. It features improved character card sensitivity and addresses common issues like 'blarbing' and 'God modding' found in previous NovelWriter versions. This model is designed for stable prompt following and diverse writing styles, making it suitable for various roleplay scenarios.

Loading preview...

OpenElla-NovelWriter-Requiem: Enhanced Roleplay and Creative Writing

N-Bot-Int's OpenElla-NovelWriter-Requiem is an 8 billion parameter model built on a Llama 3.1 base, representing a significant advancement in roleplay (RP) capabilities within the NovelWriter family. This model, specifically the 'Requiem Ascended' variant, demonstrates improved sensitivity to character cards and offers a unique blend of creative freedom for diverse RP scenarios.

Key Capabilities

  • Enhanced Roleplay: Designed to excel in various RP contexts, offering more nuanced and responsive interactions.
  • Character Card Sensitivity: Significantly improved ability to follow and integrate information from character cards.
  • Stable Prompt Following: Addresses previous issues like 'blarbing' (AI generating entire chats without user input) and 'God modding' (AI taking over character actions).
  • Diverse Writing Styles: Benefits from a 'DARE TIES' methodology, blending multiple previous NovelWriter models and datasets to achieve varied writing and dataset diversity.
  • Uncensored Nature: The model is uncensored, requiring users to handle it with ethical considerations.

Good For

  • Creative Writing: Ideal for generating creative narratives and engaging in detailed storytelling.
  • Roleplay Scenarios: Particularly suited for users seeking a model with strong character adherence and dynamic RP interactions.
  • Customization: Users can fine-tune the model further, with specific tips provided for tools like Kobold for optimal performance.

N-Bot-Int has announced a shift away from Llama bases for future models due to licensing concerns, with upcoming releases exploring Qwen or Gemma architectures. This model is released under the AGPL-3.0 license.

Finetunes
2 models