---
title: README
emoji: 💻
colorFrom: green
colorTo: blue
sdk: static
pinned: true
license: apache-2.0
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/d6FFRJ0PtDTa10VnWH9qn.jpeg
---

# 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.


![1](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/gLZPzKS6vGAIl7qh2_Qbf.png)

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

Rest in peace 4070.

---

### Our Work:

**[Gemma4NPC models](https://huggingface.co/collections/npcLM/gemma4npc)**
Our newest version of the GemmaNPC series, using the new Gemma 4 models.
- `Gemma4NPC-E4B` - larger (Recommended)
- `Gemma4NPC-E2B` - for edge devices
Both have vision and audio functining properly.

**[Gemma3NPC models](https://huggingface.co/collections/npcLM/gemma3npc-all)**

- `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

**[GemmaThink models](https://huggingface.co/collections/npcLM/gemmathink)**

- `gemma-3-1b-it-thinking-32k-grpo-merged` - The **complete** model trained on the 32k row reasoning dataset(recommended)
- `gemma-3-1b-it-thinking-20k-sft-rl` - Trained on the 20k row reasoning dataset

**[GemmaReLe](https://huggingface.co/collections/npcLM/rele)**

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

**[Finetuning Datasets](https://huggingface.co/collections/npcLM/finetuning-datasets)**
The datasets used to train our models.
- PIPPA (processed, includes original & filtered)
- NPC-Dialogue (v1 & v2)
- SonnetRolePlay
- ReLe_Synthetic_v1

**[RP Datasets](https://huggingface.co/collections/npcLM/rp-datasets)**
Individual roleplaying datasets.
- PIPPA (original & filtered)
- NPC-Dialogue (v1 & v2)
- NPC-Quest-Dialogue
- SonnetRolePlay
- ReLe_Synthetic_v1

**[Reasoning Datasets](https://huggingface.co/collections/npcLM/reasoning-datasets)**
Synthetically generated reasoning data using Qwen3-14b.
- code-thinking
- Creative-Writing-Thinking
- sciqa-thinking
- brainstorming-thinking
- gsm8k-thinking
- databricks-thinking
- cnn-summarization

Gemma3NPC **[Technical Blog](https://huggingface.co/blog/chimbiwide/gemma3npc)** 

Gemma3NPC **[Demo Video](https://youtu.be/N8-XZQ8C6kc?si=X48VmhDfSukgpSLT)**

GemmaThink **[Demo Video](https://youtu.be/MrwM3-S6DVs?si=cKUUkWeWQ-Z_ffu-)**

---

### 👥Our team:

**KeeganC**: [Github](https://github.com/KeeganCarey)

**chimbiwide**: [Github](https://github.com/chimbiwide)