Welcome to npcLM!

We are a group of students passionate about creating LLMs for roleplaying purposes and specifiaclly for video game NPCs. We aim to make live NPC interactions more accessible and immersive through fine-tuning small models.

We are very grateful for Google, Unsloth and our dear GPUs for withstanding the flames of finetuning.

Rest in peace 4070.

---

Our Work:

Gemma3NPC models

• Gemma3NPC-it - Specialized for NPC dialogues(Recommended)
• Gemma3NPC-it-beta - less conservative training parameters, performance requires further testing
• Gemma3NPC - General Roleplaying
• Gemma3NPC-filtered - filtered model, more censored

GemmaReLe

• A model finetuned specifically for ReLe, performance requires further evaluation.

Datasets

• PIPPA(processed, includes original&filtered)
• NPC-Dialogue (v1&v2)
• SonnetRolePlay
• ReLe_Synthetic_v1

Technical Blog

Demo Video

---

👥Our team:

KeeganC: Github

chimbiwide: Github