Instructions to use Chun121/qwen3-4B-rpg-roleplay with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Chun121/qwen3-4B-rpg-roleplay with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Chun121/qwen3-4B-rpg-roleplay")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Chun121/qwen3-4B-rpg-roleplay", dtype="auto")

llama-cpp-python

How to use Chun121/qwen3-4B-rpg-roleplay with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Chun121/qwen3-4B-rpg-roleplay",
	filename="gguf_f16/unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Chun121/qwen3-4B-rpg-roleplay with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

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 Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

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 Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Use Docker

docker model run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

LM Studio
Jan

vLLM

How to use Chun121/qwen3-4B-rpg-roleplay with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chun121/qwen3-4B-rpg-roleplay"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chun121/qwen3-4B-rpg-roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

SGLang

How to use Chun121/qwen3-4B-rpg-roleplay with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Chun121/qwen3-4B-rpg-roleplay" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chun121/qwen3-4B-rpg-roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Chun121/qwen3-4B-rpg-roleplay" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chun121/qwen3-4B-rpg-roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Chun121/qwen3-4B-rpg-roleplay with Ollama:
```
ollama run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
```

Unsloth Studio new

How to use Chun121/qwen3-4B-rpg-roleplay 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 Chun121/qwen3-4B-rpg-roleplay 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 Chun121/qwen3-4B-rpg-roleplay to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Chun121/qwen3-4B-rpg-roleplay to start chatting

Pi new

How to use Chun121/qwen3-4B-rpg-roleplay with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Chun121/qwen3-4B-rpg-roleplay:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Chun121/qwen3-4B-rpg-roleplay with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Chun121/qwen3-4B-rpg-roleplay with Docker Model Runner:
```
docker model run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
```

Lemonade

How to use Chun121/qwen3-4B-rpg-roleplay with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4B-rpg-roleplay-Q4_K_M

List all available models

lemonade list

A newer version of this model is available: Chun121/Qwen3-4B-RPG-Roleplay-V2

🧙‍♂️ Qwen3-4B Roleplay LoRA

Where Characters Come Alive in Conversation

Breathe life into your digital companions with natural, engaging dialogue

✨ Model Overview

Welcome, fellow creators! I'm Chun (@chun121), and I've fine-tuned the impressive Qwen3-4B model to excel at character-based conversations and roleplay scenarios. Whether you're crafting an immersive game, building an interactive storytelling platform, or developing character-driven AI experiences, this model will help your characters speak with personality, consistency, and depth.

This LoRA adaptation maintains the intelligence of the base model while enhancing its ability to:

🎭 Maintain consistent character personas
💬 Generate authentic dialogue that reflects character traits
🌍 Create immersive narrative responses
🧠 Remember context throughout conversations

📊 Technical Specifications

Feature	Details
Base Model	Qwen3-4B
Architecture	Transformer-based LLM with LoRA adaptation
Parameter Count	4 Billion (Base) + LoRA parameters
Quantization Options	4-bit (bnb), GGUF formats (Q8_0, F16, Q4_K_M)
Training Framework	Unsloth & TRL
Context Length	512 tokens
Developer	Chun
License	Apache 2.0

🧠 Training Methodology

This LoRA was trained on a free Google Colab T4 GPU using efficient quantization techniques to maximize the limited resources:

Dataset: PJMixers-Dev/Gryphe-Aesir-RPG-Charcards-Opus-Mixed-split
LoRA Configuration:
- Rank: 16
- Alpha: 32
- Target Modules: Optimized for character dialogue generation
Training Hyperparameters:
- Batch Size: 8
- Gradient Accumulation Steps: 4
- Learning Rate: 1e-4 with cosine scheduler
- Max Steps: 200
- Precision: FP16/BF16 (auto-detected)
- Packing: Enabled for efficient training
- QLoRA: 4-bit quantization via bitsandbytes

📚 Dataset Deep Dive

The Gryphe-Aesir-RPG-Charcards-Opus-Mixed-split dataset is a rich collection of character interactions featuring:

Diverse character archetypes across different genres
Multi-turn conversations that maintain character consistency
Varied emotional contexts and scenarios
Rich descriptive language and character-driven responses

This carefully curated dataset helps the model understand the nuances of character voices, maintaining consistent personalities while generating engaging responses.

🚀 Getting Started

Hugging Face Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model with 4-bit quantization for efficiency
tokenizer = AutoTokenizer.from_pretrained("chun121/qwen3-4b-roleplay-lora")
model = AutoModelForCausalLM.from_pretrained(
    "chun121/qwen3-4b-roleplay-lora",
    torch_dtype=torch.float16,  # Use float16 for faster inference
    device_map="auto"           # Automatically choose best device
)

# Create a character-focused prompt
character_prompt = """
Character: Elara, an elven mage with centuries of knowledge but little patience for novices
Setting: The Grand Library of Mystral
Context: A young apprentice has asked for help with a difficult spell

User: Excuse me, I'm having trouble with the fire conjuration spell. Could you help me?

Elara:
"""

# Generate response
inputs = tokenizer(character_prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    inputs["input_ids"],
    max_new_tokens=200,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Using GGUF Models

If you're utilizing the GGUF exports with llama.cpp:

# Example command for Q4_K_M quantization
./llama -m chun121-qwen3-4b-roleplay-lora.Q4_K_M.gguf -p "Character: Elara, an elven mage..." -n 200

💡 Recommended Usage

This model works best when:

Providing character context: Include a brief description of the character's personality, background, and current situation
Setting the scene: Give context about the environment and circumstances
Using chat format: Structure inputs as a conversation between User/Human and Character
Maintaining temperature: Values between 0.7-0.8 offer a good balance of creativity and coherence

🔄 Limitations

Limited to 512 token context window
May occasionally "forget" character traits in very long conversations
Training dataset focuses primarily on fantasy/RPG contexts
As a LoRA fine-tune, inherits limitations of the base Qwen3-4B model

🔗 Related Projects

If you enjoy this model, check out these related projects:

🙏 Acknowledgements

Special thanks to:

The Qwen team for their incredible base model
PJMixers-Dev for the high-quality dataset
The Unsloth team for making efficient fine-tuning accessible
The HuggingFace community for their continued support

📬 Feedback & Contact

I'd love to hear how this model works for your projects! Feel free to:

Open an issue on the HuggingFace repo
Connect with me on HuggingFace @chun121
Share examples of characters you've created with this model

May your characters speak with voices that feel truly alive!

Created with ❤️ by Chun

Downloads last month: 262

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

16-bit

Chun121
/

qwen3-4B-rpg-roleplay