Instructions to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="devmeta/Llama-3-8B-Racing-Level-Design-Expert",
	filename="llama-3-8b.Q4_K_M_Racing_Level_Design.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING
# Run inference directly in the terminal:
llama-cli -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING
# Run inference directly in the terminal:
llama-cli -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING
# Run inference directly in the terminal:
./llama-cli -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING
# Run inference directly in the terminal:
./build/bin/llama-cli -hf devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

Use Docker

docker model run hf.co/devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

LM Studio
Jan

Ollama

How to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with Ollama:

ollama run hf.co/devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

Unsloth Studio new

How to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for devmeta/Llama-3-8B-Racing-Level-Design-Expert to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for devmeta/Llama-3-8B-Racing-Level-Design-Expert to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for devmeta/Llama-3-8B-Racing-Level-Design-Expert to start chatting

Docker Model Runner
How to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with Docker Model Runner:
```
docker model run hf.co/devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING
```

Lemonade

How to use devmeta/Llama-3-8B-Racing-Level-Design-Expert with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull devmeta/Llama-3-8B-Racing-Level-Design-Expert:Q4_K_M_RACING

Run and chat with the model

lemonade run user.Llama-3-8B-Racing-Level-Design-Expert-Q4_K_M_RACING

List all available models

lemonade list

devmeta commited on Dec 26, 2025

Commit

bddad62

verified ·

1 Parent(s): 1ee4a04

Update README.md

Browse files

Files changed (1) hide show

README.md +45 -3

README.md CHANGED Viewed

@@ -1,3 +1,45 @@
----
-license: cc-by-4.0
----

+---
+license: cc-by-4.0
+---
+# Llama-3-8B-Racing-Level-Design-Expert (GGUF)
+## 1. Model Summary (모델 개요)
+**[EN]** This model is a specialized Small Language Model (SLM) fine-tuned for analyzing racing game level design components and player preferences. It integrates 20+ years of industry expertise from Nexon (KartRider series) with academic research data.
+**[KR]** 본 모델은 레이싱 게임 레벨 디자인의 구성 요소와 플레이어 선호도를 분석하기 위해 파인튜닝된 SLM(Small Language Model)입니다. 넥슨 《카트라이더》 시리즈에서 20년 이상 쌓은 실무 노하우와 학술적 데이터를 결합하였습니다.
+## 2. About the Author
+### Kim Tae-Wan
+* **Current Role**: Game Developer & Researcher at NEXON (20+ years of experience)
+* **Academic Background**:
+    * Ph.D. Student in Technology at Sogang University Graduate School of Metaverse
+    * M.S. in Game Design from Gachon University
+    * B.F.A. from Pusan National University
+* **Expertise**: Level Design for the *KartRider* series, World Building Systems, and LLM-based Content Pipelines.
+## 3. Research Context (연구 배경)
+**[EN]** The training dataset is based on the author's Master's thesis, which identifies 19 key level design variables and their impact on player satisfaction.
+**[KR]** 본 모델의 학습 데이터셋은 저자의 석사 학위 논문을 바탕으로 합니다. 레이싱 게임의 19가지 핵심 레벨 디자인 변수(예각 커브, 헤어핀, 가속 트리거 등)와 유저 만족도 간의 상관관계를 학습하였습니다.
+### Key Research Variables (핵심 연구 변수):
+* Acute Curves (예각 커브)
+* Hairpin Turns (헤어핀)
+* Acceleration Triggers (가속 트리거)
+* Verticality and Slopes (고저차 및 경사로)
+* Visibility and Obstacles (시야 및 장애물)
+## 4. Intended Use (주요 용도)
+* **Design Automation**: Automated analysis of track structures during the planning stage.
+* **Preference Prediction**: Evaluating the potential success of a track based on player preference data.
+* **Research Integration**: Part of the "VN Studio" and "Persona AI System" projects for automated game content generation.
+## 5. Technical Details (기술 사양)
+* **Base Model**: Llama-3-8B (4-bit quantized)
+* **Format**: GGUF (Optimized for local inference via LM Studio/Ollama)
+* **Training Method**: Supervised Fine-Tuning (SFT) using Unsloth
+## 6. Reference & Citation (인용 및 참고문헌)
+**Thesis**: *A Study on Level Design Components and Player Preferences in Racing Game Content* (Gachon Univ.)
+* **Link**: https://www.dbpia.co.kr/journal/detail?nodeId=T14760144
+---
+**Contact**: https://github.com/Taewan627