base_model, tags, license, language, datasets

base_model	tags	license	language	datasets
unsloth/Qwen3-4B	text-generation-inference transformers unsloth qwen3 ui-generation react typescript shadcn finetuned	apache-2.0	en	iamdyeus/ui-instruct-4k

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:

• "Build a hero section with a headline, subtitle, and two CTA buttons"
• "Create a sidebar navigation with icons and collapsible sections"

---

Links

• 📦 GGUF repo: iamdyeus/qwendean-4b-GGUF