OccultAI/DeepWater-Pleroma-24B-v1
OccultAI/DeepWater-Pleroma-24B-v1 is a 24 billion parameter experimental language model developed by OccultAI, featuring a 32768 token context length. It is an instruction-tuned model, fine-tuned on a private dataset of translated posts and further augmented by the Mag Mell MPOA dataset. This model is specifically designed for generating narratives and roleplay, including content that may be violent and graphically erotic, and is optimized for use with the Mistral Tekken template.
Loading preview...
DeepWater Pleroma 24B v1 Overview
DeepWater Pleroma 24B v1 is an experimental 24 billion parameter language model developed by OccultAI. It has been fine-tuned on a unique private dataset consisting of translated posts, with further augmentation from the Mag Mell MPOA dataset. This model is notable for its 32768 token context length, allowing for extended and complex interactions.
Key Capabilities
- Narrative Generation: Excels at creating detailed and immersive narratives.
- Roleplay (RP): Optimized for engaging in roleplay scenarios.
- Explicit Content Generation: Capable of producing content that includes violent and graphic erotic themes.
Good For
- Users seeking a model for generating explicit and mature narratives or roleplay content.
- Applications requiring a model fine-tuned on unique, translated post datasets.
- Developers looking to leverage a model with a large context window for extended interactions.
- Best performance is achieved when utilizing the Mistral Tekken template for prompts.