DoppelReflEx/MiniusLight-24B

TEXT GENERATIONPricing:Input $0.7 / Cached $0.04 / Output $1.16Concurrent Unit Cost:2Model Size:24BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 7, 2025License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

MiniusLight-24B by DoppelReflEx is a 24 billion parameter language model with a 32768 token context length, created through a Slerp merge of TheDrummer/Cydonia-24B-v2 and PocketDoc/Dans-PersonalityEngine-V1.2.0-24b. This model is optimized for strong performance in ERP, roleplay, and story writing, making it suitable for creative text generation tasks. It utilizes the ChatML chat template and is available in GGUF format.

Loading preview...

Overview

MiniusLight-24B is a 24 billion parameter language model developed by DoppelReflEx, built upon a Slerp merge of two Mistral-based models: TheDrummer/Cydonia-24B-v2 and PocketDoc/Dans-PersonalityEngine-V1.2.0-24b. This model is designed to offer a balanced performance across various creative and interactive text generation tasks, leveraging the strengths of its constituent models.

Key Capabilities

  • Enhanced Roleplay (ERP): Strong performance in generating engaging and coherent roleplay scenarios.
  • Story Writing: Excels at crafting detailed and imaginative narratives.
  • General Purpose Text Generation: Suitable for a wide range of creative text outputs.
  • ChatML Support: Utilizes the ChatML chat template for structured conversations.

Good For

  • Developers and enthusiasts looking for a capable model for creative writing projects.
  • Applications requiring interactive roleplay or character-driven narratives.
  • Experimentation with merged models and their performance characteristics.
  • Users seeking a model with a 32768 token context length for longer interactions.

Finetunes
12 models