DoppelReflEx/MN-12B-Mimicore-Orochi
DoppelReflEx/MN-12B-Mimicore-Orochi is a 12.2 billion parameter merged language model with a 32768 token context length, developed by DoppelReflEx. It is a variant of the WhiteSnake model, specifically optimized for roleplay (RP), erotic roleplay (ERP), and storytelling applications. While slightly lower in evaluation scores compared to its WhiteSnake counterpart, it maintains strong performance in creative text generation tasks.
Loading preview...
Overview
DoppelReflEx/MN-12B-Mimicore-Orochi is a 12.2 billion parameter language model, a variant within the Mimicore series, offering a 32768 token context length. It is a merged model, built upon IntervitensInc/Mistral-Nemo-Base-2407-chatml and incorporating components from DoppelReflEx/MN-12B-Mimicore-GreenSnake, cgato/Nemo-12b-Humanize-KTO-Experimental-Latest, and Epiculous/Violet_Twilight-v0.2 using the dare_ties merge method.
Key Capabilities
- Creative Text Generation: Designed for generating engaging and coherent content for roleplay, erotic roleplay, and storytelling scenarios.
- Extended Context: Supports a 32768 token context window, allowing for longer and more complex narrative interactions.
- Merged Architecture: Benefits from the combined strengths of multiple base models, aiming for specialized performance in its target applications.
Good For
- Roleplay (RP) and Erotic Roleplay (ERP): Excels at maintaining character consistency and narrative flow in interactive roleplaying.
- Storytelling: Suitable for generating creative narratives and expanding plotlines.
- Experimental Use: Users should be aware of a rare, random tokenization issue inherited from one of its merged components, which can typically be resolved by regenerating the response.