Aratako/Mistral-Nemo-12B-RP
Aratako/Mistral-Nemo-12B-RP is a 12 billion parameter language model developed by Aratako, fine-tuned specifically for role-playing tasks. Based on mistralai/Mistral-Nemo-Instruct-2407, this model excels at generating character-driven dialogues and narratives within a specified context. It supports a context length of 32768 tokens, making it suitable for detailed and extended role-play scenarios.
Loading preview...
Model Overview
Aratako/Mistral-Nemo-12B-RP is a 12 billion parameter model developed by Aratako, built upon the mistralai/Mistral-Nemo-Instruct-2407 base model. Its primary distinction lies in its specialized fine-tuning for role-playing applications, enabling it to generate character-consistent responses within defined scenarios.
Key Capabilities
- Specialized Role-Playing: Designed to embody specific characters and engage in contextual dialogues based on detailed system prompts.
- Extended Context Handling: Supports a substantial context length of 32768 tokens, allowing for complex and prolonged role-play interactions.
- Chat Template Adherence: Utilizes a specific chat template (
<|im_start|>system,<|im_start|>user,<|im_start|>assistant) for structured input and output, facilitating consistent character portrayal.
Recommended Usage
This model is ideal for developers and creators looking to implement AI-driven role-play experiences. Users should provide comprehensive character settings, dialogue situations, and world-building details within the system prompt to guide the model's responses. Examples provided demonstrate its use with ollama and vLLM, showcasing how to set up detailed role-play scenarios and generate varied character outputs. It is suggested to use lower temperatures (e.g., 0.3) for more consistent and focused role-play generation, as recommended for its base model.