vicgalle/Roleplay-Mistral-7B

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jun 9, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

vicgalle/Roleplay-Mistral-7B is a 7 billion parameter Mistral-Instruct-7B-v0.2 model fine-tuned for roleplay scenarios. It specializes in generating dialogue and actions in a specific format, making it suitable for interactive narrative applications. This model was fine-tuned using the ResplendentAI/NSFW_RP_Format_DPO dataset, focusing on structured roleplay outputs. Its 4096-token context window supports engaging and coherent roleplay interactions.

Loading preview...

Model Overview

vicgalle/Roleplay-Mistral-7B is a specialized 7 billion parameter language model based on the Mistral-Instruct-7B-v0.2 architecture. It has been fine-tuned to excel in roleplay generation, specifically producing outputs that follow a "dialogue action" format.

Key Capabilities

  • Structured Roleplay Generation: Outputs text in a consistent dialogue and action format, ideal for interactive storytelling.
  • Fine-tuned for Roleplay: Optimized using the ResplendentAI/NSFW_RP_Format_DPO dataset, enhancing its ability to create engaging roleplay content.
  • Mistral-7B Foundation: Benefits from the strong base capabilities of the Mistral-Instruct-7B-v0.2 model.

Good For

  • Interactive Fiction and Games: Generating character dialogue and actions for text-based games or narrative experiences.
  • Creative Writing Tools: Assisting writers in developing roleplay scenarios with structured outputs.
  • Personalized Roleplay Applications: Creating custom roleplay interactions where a specific output format is desired.