---
base_model: openbmb/MiniCPM5-1B
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:openbmb/MiniCPM5-1B
- lora
- sft
- transformers
- trl
---

# Model Card for NPC Brain

This is a fine-tune of Open BMB's Mini CPM5 1B parameter model. 

I have specifically trained it to be the "Brain" of my app for the Build Small Hackathon in June 2026



- **Developed by:** mecoffey
- **Model type:** Causal Language Model
- **Language:** English
- **License:** apache-2.0
- **Finetuned from model:** https://huggingface.co/openbmb/MiniCPM5-1B
- **Total Parameters after fine-tune** 1,080,632,832



### Recommendations

This model was trained with the following workflow in mind:

- User prompt = physical description of a fantasy character.
- User prompt + generated description = a timeline backstory for the character to get to know them. 

The user prompt is designed to be short and simple. "something random", "a farmer" "a Half-Orc barkeep with a noticeable scar"


## Training Details

### Training Data

https://huggingface.co/datasets/mecoffey/npc_dataset


### Compute Infrastructure

Trained with Modal GPUs

## Citation

@article{minicpm4,
  title={Minicpm4: Ultra-efficient llms on end devices},
  author={MiniCPM, Team},
  journal={arXiv preprint arXiv:2506.07900},
  year={2025}
}