tlacuilo-12b
**Tlacuilo-12B** is a 12-billion-parameter fine-tuned language model developed by Allura Org, based on **Mistral-Nemo-Base-2407** and **Muse-12B**, optimized for high-quality creative writing, roleplay, and narrative generation. Trained using a three-stage QLoRA process with diverse datasets—including literary texts, roleplay content, and instruction-following data—the model excels in coherent, expressive, and stylistically rich prose.
Key features:
- **Base models**: Built on Mistral-Nemo-Base-2407 and Muse-12B for strong reasoning and narrative capability.
- **Fine-tuned for creativity**: Optimized for roleplay, storytelling, and imaginative writing with natural, fluid prose.
- **Chat template**: Uses **ChatML**, making it compatible with standard conversational interfaces.
- **Recommended settings**: Works well with temperature 1.0–1.3 and min-p 0.02–0.05 for balanced, engaging responses.
Ideal for writers, game masters, and creative professionals seeking a versatile, high-performance model for narrative tasks.
> *Note: The GGUF quantized version (e.g., `Ennthen/Tlacuilo-12B-Q4_K_M-GGUF`) is a conversion of this base model for local inference via llama.cpp.*