---
language:
- en
license: mit
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- lora
- fine-tuned
- rpg
- basic-fantasy
- bfrpg
- tabletop
datasets:
- custom
pipeline_tag: text-generation
---

# Phi-3 Mini 4K Instruct — BFRPG Fine-Tune

A fine-tuned version of [Microsoft Phi-3 Mini 4K Instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) trained on Basic Fantasy Role-Playing Game (BFRPG) Thief abilities rules Q&A.

## Model Details

| Property | Value |
|----------|-------|
| **Base Model** | [Microsoft Phi-3 Mini 4K Instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) |
| **Parameters** | ~3.8B |
| **Fine-Tuning Method** | LoRA SFT (merged) |
| **Precision** | bfloat16 |
| **LoRA Rank** | 16 |
| **LoRA Alpha** | 32 |
| **LoRA Dropout** | 0.05 |
| **Epochs** | 5 |
| **Batch Size** | 4 |
| **Learning Rate** | 2e-4 |
| **Hardware** | NVIDIA DGX Spark (GB10 Blackwell) |

## Training Data

8 synthetic Q&A pairs generated from the Basic Fantasy RPG rulebook, focused on Thief class abilities (Open Locks, Pick Pockets, Move Silently, etc.). Data was generated using an LLM-based synthetic data generation pipeline with faithfulness judging.

The model uses the following system prompt:

> You are a rules expert for the Basic Fantasy Role-Playing Game. Answer questions accurately based on the official rules. Be specific and cite page references or table values where possible.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("FrankDigsData/phi3-mini-rhai-finetuned")
tokenizer = AutoTokenizer.from_pretrained("FrankDigsData/phi3-mini-rhai-finetuned")

messages = [
    {"role": "system", "content": "You are a rules expert for the Basic Fantasy Role-Playing Game. Answer questions accurately based on the official rules."},
    {"role": "user", "content": "What is a level 5 Thief's Pick Pockets score?"}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Context

This model was fine-tuned as part of a Red Hat AI workshop comparing small model adaptation techniques across multiple architectures.