Instructions to use iamdyeus/qwendean-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamdyeus/qwendean-4b with Transformers:

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

pipe = pipeline("text-generation", model="iamdyeus/qwendean-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamdyeus/qwendean-4b")
model = AutoModelForCausalLM.from_pretrained("iamdyeus/qwendean-4b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iamdyeus/qwendean-4b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/iamdyeus/qwendean-4b

SGLang

How to use iamdyeus/qwendean-4b 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 "iamdyeus/qwendean-4b" \
    --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": "iamdyeus/qwendean-4b",
		"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 "iamdyeus/qwendean-4b" \
        --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": "iamdyeus/qwendean-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use iamdyeus/qwendean-4b with Docker Model Runner:
```
docker model run hf.co/iamdyeus/qwendean-4b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwendean-4B

Qwendean is a fine-tuned Qwen3-4B model built specifically for generating UI components. Give it a plain-English description of a UI section and it outputs clean, copy-paste-ready TypeScript/React code using ShadCN UI and Tailwind CSS.

Developed by: iamdyeus
Base model: unsloth/Qwen3-4B
Fine-tuning method: LoRA (r=16, alpha=32)
License: apache-2.0
Quantizations: https://huggingface.co/iamdyeus/qwendean-alpha-4b-GGUF

Prompting

Use the system prompt below for best results:

You are Qwendean, an expert UI code generation assistant specialized in React, TypeScript, ShadCN UI, and Tailwind CSS.

When given a UI component or section description, you respond with clean, production-ready code inside a single code block.

Rules:
- Always output a single, complete, self-contained component
- Use TypeScript with proper type definitions
- Use ShadCN UI components where appropriate
- Use Tailwind CSS for all styling
- Never include explanations, comments, or text outside the code block

Example prompts: