DoppelReflEx/MN-12B-WolFrame

TEXT GENERATIONPricing:Input $1.2 / Output $4.8Concurrent Unit Cost:1Model Size:12.2BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jan 29, 2025License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

DoppelReflEx/MN-12B-WolFrame is a 12.2 billion parameter language model developed by DoppelReflEx, built upon the Mistral-Nemo-Base-2407-chatml architecture. This model is specifically optimized for creative writing, roleplay (RP), and erotic roleplay (ERP) tasks, offering a decent performance in these areas. It is not recommended for mathematical tasks. The model has a context length of 32768 tokens.

Loading preview...

DoppelReflEx/MN-12B-WolFrame Overview

DoppelReflEx/MN-12B-WolFrame is a 12.2 billion parameter language model developed by DoppelReflEx, designed with a primary focus on creative writing and roleplay scenarios. This model, previously known as WhiteSnake-V2, was created to improve upon its predecessor's evaluation scores and real-world applicability. It is built on the Mistral-Nemo-Base-2407-chatml architecture and incorporates a merge of several models, including crestf411/MN-Slush, DoppelReflEx/MN-12B-Mimicore-GreenSnake, and cgato/Nemo-12b-Humanize-KTO-Experimental-Latest, using the dare_ties merge method.

Key Capabilities

  • Creative Writing: Excels at generating imaginative and engaging text for various creative purposes.
  • Roleplay (RP) & Erotic Roleplay (ERP): Optimized for interactive storytelling and character-driven narratives.

Good For

  • Applications requiring high-quality creative text generation.
  • Interactive fiction and chatbot development focused on roleplaying.
  • Scenarios where detailed and immersive narrative responses are crucial.

Limitations

  • The model is explicitly noted as not good in Math, indicating it is unsuitable for mathematical reasoning or problem-solving tasks.

Finetunes
3 models