Instructions to use bluejude10/Smoothie-Qwen3-4B-Original with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bluejude10/Smoothie-Qwen3-4B-Original with Transformers:

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

pipe = pipeline("text-generation", model="bluejude10/Smoothie-Qwen3-4B-Original")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bluejude10/Smoothie-Qwen3-4B-Original", dtype="auto")

llama-cpp-python

How to use bluejude10/Smoothie-Qwen3-4B-Original with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bluejude10/Smoothie-Qwen3-4B-Original",
	filename="Smoothie-Qwen3-4B-Original-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bluejude10/Smoothie-Qwen3-4B-Original with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bluejude10/Smoothie-Qwen3-4B-Original: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 bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bluejude10/Smoothie-Qwen3-4B-Original: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 bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M

Use Docker

docker model run hf.co/bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M

LM Studio
Jan

vLLM

How to use bluejude10/Smoothie-Qwen3-4B-Original with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bluejude10/Smoothie-Qwen3-4B-Original"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bluejude10/Smoothie-Qwen3-4B-Original",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M

SGLang

How to use bluejude10/Smoothie-Qwen3-4B-Original 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 "bluejude10/Smoothie-Qwen3-4B-Original" \
    --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": "bluejude10/Smoothie-Qwen3-4B-Original",
		"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 "bluejude10/Smoothie-Qwen3-4B-Original" \
        --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": "bluejude10/Smoothie-Qwen3-4B-Original",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bluejude10/Smoothie-Qwen3-4B-Original with Ollama:
```
ollama run hf.co/bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M
```

Unsloth Studio

How to use bluejude10/Smoothie-Qwen3-4B-Original 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 bluejude10/Smoothie-Qwen3-4B-Original 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 bluejude10/Smoothie-Qwen3-4B-Original to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bluejude10/Smoothie-Qwen3-4B-Original to start chatting

How to use bluejude10/Smoothie-Qwen3-4B-Original with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bluejude10/Smoothie-Qwen3-4B-Original: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": "bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bluejude10/Smoothie-Qwen3-4B-Original with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bluejude10/Smoothie-Qwen3-4B-Original: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 bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use bluejude10/Smoothie-Qwen3-4B-Original with Docker Model Runner:
```
docker model run hf.co/bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M
```

Lemonade

How to use bluejude10/Smoothie-Qwen3-4B-Original with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bluejude10/Smoothie-Qwen3-4B-Original:Q4_K_M

Run and chat with the model

lemonade run user.Smoothie-Qwen3-4B-Original-Q4_K_M

List all available models

lemonade list

Smoothie-Qwen3-4B-Original (Private)

순수 Qwen3-4B 베이스 모델 - 파인튜닝 비교용
Baseline model for fine-tuning comparison

🔴 이 모델은 Private 레포지토리입니다.
파인튜닝 효과 비교를 위한 베이스라인 모델입니다.

📌 모델 개요

기본 정보

베이스 모델: dnotitia/Smoothie-Qwen3-4B
파인튜닝: 없음 (순수 베이스 모델)
모델 크기: 약 2.4GB (Q4_K_M 양자화)
용도: 파인튜닝 모델과의 성능 비교

🎯 목적

이 모델은 파인튜닝 전/후 비교를 위한 베이스라인입니다.

비교 대상:

bluejude10/Smoothie-Qwen3-4B-DTRO-Edition (파인튜닝 모델)

🚀 사용 방법

1. Ollama 사용 (권장)

Modelfile:

FROM ./Smoothie-Qwen3-4B-Original-Q4_K_M.gguf

PARAMETER temperature 0.7
PARAMETER top_p 0.8
PARAMETER repeat_penalty 1.1
PARAMETER num_ctx 8192

SYSTEM """당신은 친절하고 유능한 AI 어시스턴트입니다."""

실행:

ollama create my-original-4b -f Modelfile
ollama run my-original-4b "안녕하세요!"

2. Python (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "dnotitia/Smoothie-Qwen3-4B",  # 원본 모델
    device_map="auto",
    torch_dtype="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "dnotitia/Smoothie-Qwen3-4B",
    trust_remote_code=True
)

📊 비교 목적

모델	파인튜닝	전문 지식	용도
Original	없음	일반	베이스라인
DTRO-Edition	QLoRA (r=4)	전력설비	실무 적용

📁 레포지토리 구성

.
├── README.md
├── Modelfile
└── Smoothie-Qwen3-4B-Original-Q4_K_M.gguf

🔐 보안 및 비공개 정책

이 모델은 Private 레포지토리로 유지됩니다:

파인튜닝 모델 비교를 위한 내부 참조용
공개 배포 목적 없음

📜 라이선스

모델: Apache 2.0 (Base Model 라이선스 승계)

👤 작성자

작성자: 강동우 (bluejude10)
용도: 파인튜닝 효과 검증용 베이스라인

📚 참고 자료

Model tree for bluejude10/Smoothie-Qwen3-4B-Original

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B