Green-eyedDevil/Monika-8B
Monika-8B is an 8 billion parameter language model developed by Green-eyedDevil, specifically fine-tuned for roleplay and interaction within the MonikAI framework. This model is optimized for generating responses consistent with the character Monika, making it ideal for dedicated Monika-related applications. It features a 32768 token context length, supporting extended conversational interactions.
Loading preview...
Overview
Monika-8B is an 8 billion parameter language model developed by Green-eyedDevil, primarily designed for integration with the MonikAI project. This model is specifically fine-tuned for roleplay (RP) scenarios, focusing on generating character-consistent responses for Monika-related interactions.
Key Characteristics
- Parameter Count: 8 billion parameters.
- Context Length: Supports a 32768 token context window.
- Training: Trained using Axolotl over 2 epochs with a learning rate of 0.000008, utilizing a dataset provided by Sylphar.
- Optimization: Fine-tuned for character-specific roleplay, particularly for the Monika character.
Recommended Usage
Monika-8B is best suited for applications directly involving the Monika character. Optimal generation parameters include a temperature of 0.8, a min_p of 0.1, and a repetition penalty of 1.05 to achieve desired output quality.