UIGEN T1.5 14B

🚀 UIGEN-T1.5 Model Card

UIGEN-T1.5 is an advanced UI generation model based on the transformer architecture. It is fine - tuned from Qwen2.5 - Coder - 14B - Instruct, aiming to generate stunning, modern, and unique frontend user interfaces.

Landing page showcasing visual richness

🚀 Quick Start

UIGEN-T1.5 can generate high - quality HTML and CSS code for various frontend interfaces. You can use it by following the inference example below.

✨ Features

• Advanced UI Styles: It can create sleek, modern, and unique designs.
• Chain - of - Thought Reasoning: Enhanced reasoning capabilities ensure accurate HTML/CSS layouts.
• High Usability: Generates responsive and production - ready frontend code.

📦 Installation

The README does not provide installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "smirki/UIGEN-T1.5"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda")

prompt = """<|im_start|>user
Design a sleek, modern dashboard for monitoring solar panel efficiency.<|im_end|>
<|im_start|>assistant
<|im_start|>think
"""

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=12012, do_sample=True, temperature=0.7)

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

📚 Documentation

Use Cases

Recommended Uses

• Dashboards: Create insightful and visually appealing data interfaces.
• Landing Pages: Design captivating and high - conversion web pages.
• Authentication Screens: Build elegant sign - up and login interfaces.

Limitations

• Limited Interactivity: It has minimal JavaScript functionality, mainly focusing on HTML/CSS.
• Prompt Engineering: Specific prompts (e.g., appending "answer") may be required.

Performance and Evaluation

• Strengths:
  • High - quality UI generation.
  • Strong reasoning capabilities for structured layouts.
• Weaknesses:
  • Occasional repetitive design patterns.
  • Minor artifacting in complex designs.

Visual Examples

Dashboard UI generated by UIGEN-T1.5

🔧 Technical Details

• Architecture: Transformer - based LLM
• Base Model: Qwen2.5 - Coder - 7B - Instruct
• Precision: bf16 mixed precision, quantized to q8
• Hardware Requirements: Recommended 12GB VRAM
• Software Dependencies:
  • Hugging Face Transformers
  • PyTorch

📄 License

The model is licensed under the apache - 2.0 license.

📚 Citation

@misc{Tesslate_UIGEN-T1.5,
  title={UIGEN-T1.5: Advanced Chain-of-Thought UI Generation Model},
  author={smirki},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/Tesslate/UIGEN-T1.5}
}

🤝 Contact & Community

• Creator: smirki
• Repository & Demo: Coming soon!

Sponsored by vichar ai Huggingface Website