đ UIGEN-T1.5 Model Card
UIGEN-T1.5 is an advanced UI generation model based on transformers. It is fine - tuned from Qwen2.5 - Coder - 32B - Instruct and can generate stunning, modern, and unique frontend user interfaces.
Landing page showcasing visual richness
đ Quick Start
Inference Example
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))
⨠Features
- Advanced UI Styles: Produces sleek, modern, and unique designs.
- Chain-of-Thought Reasoning: Enhanced reasoning capabilities for accurate HTML/CSS layouts.
- High Usability: Generates responsive and production-ready frontend code.
đ Documentation
Model Overview
UIGEN-T1.5 is an advanced transformer-based UI generation model fine-tuned from Qwen2.5-Coder-32B-Instruct, specifically enhanced to produce stunning, modern, and unique frontend user interfaces. Leveraging sophisticated reasoning and chain-of-thought methodologies, UIGEN-T1.5 excels at generating highly structured and visually compelling HTML and CSS code, ideal for sleek dashboards, engaging landing pages, and intuitive sign-up forms.
Visual Examples
See examples below showcasing UIGEN-T1.5-generated interfaces:
Dashboard UI generated by UIGEN-T1.5
Use Cases
Recommended Uses
- Dashboards: Insightful and visually appealing data interfaces.
- Landing Pages: Captivating and high-conversion web pages.
- Authentication Screens: Elegant sign-up and login interfaces.
Limitations
- Limited Interactivity: Minimal JavaScript functionality, focusing on HTML/CSS.
- Prompt Engineering: May require specific prompts (e.g., appending "answer").
Performance and Evaluation
- Strengths:
- High-quality UI generation.
- Strong reasoning capabilities for structured layouts.
- Weaknesses:
- Occasional repetitive design patterns.
- Minor artifacting in complex designs.
Technical Specifications
| Property |
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 |
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
đ License
This model is licensed under the apache-2.0 license.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
