character roleplay, creative writing, general intelligence
Use Cases
Areas:
roleplay, creative writing, general intelligence
Primary Use Cases:
exceptional character roleplay, creative writing
Additional Notes
Fine-tuned using the Direct Preference Optimization method. This model requires advanced hardware (A100 GPU) for fine-tuning, suggesting possible high computational needs.
Training Details
Data Sources:
ResplendentAI/NSFW_RP_Format_DPO
Methodology:
Direct Preference Optimization (DPO)
Hardware Used:
A100 on Google Colab
Model Architecture:
LoRA, AutoModelForCausalLM with specific configuration for causal language modeling.