Files
UIGEN-T3-4B-Preview-MAX/README.md

169 lines
6.0 KiB
Markdown
Raw Normal View History

---
base_model:
- Qwen/Qwen3-4B
tags:
- text-generation-inference
- transformers
- qwen3
- ui-generation
- tailwind-css
- html
language:
- en
---
# UIGEN-T3 — Advanced UI Generation with Hybrid Reasoning
> Tesslates next-gen UI model, built for thoughtful design.
---
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/fqZE717ubrgSpAOHeMEeQ.png" alt="UIGEN-T3 UI Screenshot 1" width="500">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/N5gfKRD-j9JAeMoGy7O3K.png" alt="UIGEN-T3 UI Screenshot 2" width="500">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/PDGXycDkVsxFRxqHc6TKD.png" alt="UIGEN-T3 UI Screenshot 2" width="500">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/Q4CHYYcDAN60NFjIPVQnH.png" alt="UIGEN-T3 UI Screenshot 3" width="500">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ePZoCA8lS4Y1KdkchrTlQ.png" alt="UIGEN-T3 UI Screenshot 4" width="500">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/BU-Pk2moNsTOGuYF1XuRx.png" alt="UIGEN-T3 UI Screenshot 5" width="500">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/gz5ub0lDpS-hhw1MB7e07.png" alt="UIGEN-T3 UI Screenshot 6" width="500">
## Demos
Explore New UI generations:
📂 [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
---
**Join our Discord:** [https://discord.gg/GNbWAeJ4](https://discord.gg/GNbWAeJ4)
**Our Website:** [https://tesslate.com](https://tesslate.com)
## Quick Information
* **UI generation model** built on **Qwen3 architecture**
* Supports both **components** and **full web pages**
* **Hybrid reasoning system**: Use `/think` or `/no_think` modes
* Powered by **UIGenEval**, a first-of-its-kind benchmark for UI generation
* Released for **research, non-commercial use.** If you want to use it commercially, please contact us for a pilot program.
---
## Model Details
* **Base Model**: Qwen/Qwen3-4B
* **Reasoning Style**: Hybrid (`/think` and `/no_think`)
* **Tokenizer**: Qwen default, with design token headers
* **Output**: Components + Full pages (with `<html>`, `<head>`)
* **Images**: User-supplied or placehold.co no images in the dataset due to licensing concerns.
* **License**: Research only (non-commercial). Contact us for enterprise use cases.
---
## Reasoning System
UIGEN-T3 was trained using a **pre/post reasoning model architecture**.
You can explicitly control the reasoning mode:
* `/think` → Enables guided reasoning with layout analysis and heuristics.
* `/no_think` → Faster, raw code generation.
Outputs also include **design tokens** at the top of each generation for easier site-wide customization.
---
## Inference Parameters
Please use 20k context length to get the best results if using reasoning.
| Parameter | Value |
| :---------- | :---- |
| Temperature | 0.6 |
| Top P | 0.95 |
| Top K | 20 |
| Max Tokens | 40k+ |
---
## Evaluation: UIGenEval Framework
**UIGenEval** is our internal evaluation suite, designed to **bridge the gap** between creative output and quality assurance.
*(Learn more in our upcoming paper: "UIGenEval: Bridging the Evaluation Gap in AI-Driven UI Generation" - August, 2025)*
UIGenEval evaluates models across four pillars:
1. **Technical Quality** — Clean HTML, CSS structure, semantic accuracy.
2. **Prompt Adherence** — Feature completeness and fidelity to instructions.
3. **Interaction Behavior** — Dynamic logic hooks and functional interactivity.
4. **Responsive Design** — Multi-viewport performance via Lighthouse, Axe-core, and custom scripts.
This comprehensive framework directly informs our **GRPO reward functions** for the next release.
---
## Example Prompts to Try
* `make a google drive clone`
* `build a figma-style canvas with toolbar`
* `create a modern pricing page with three plans`
* `generate a mobile-first recipe sharing app layout`
---
## Use Cases
| Use Case | Description |
| :---------------------- | :-------------------------------------------------------------------------- |
| **Startup MVPs** | Quickly scaffold UIs from scratch with clean code. |
| **Design-to-Code Transfer** | Figma (coming soon) → Code generation. |
| **Component Libraries** | Build buttons, cards, navbars, and export at scale. |
| **Internal Tool Builders** | Create admin panels, dashboards, and layout templates. |
| **Rapid Client Prototypes** | Save time on mockups with production-ready HTML+Tailwind outputs. |
---
## Limitations
* No Bootstrap support (planned).
* Not suited for production use — **research-only license**.
* Responsive tuning varies across output complexity.
---
## Roadmap
| Milestone | Status |
| :-------------------------- | :----- |
| Launch Tesslate Designer | 2 days |
| Figma convert | |
| Bootstrap & JS logic | |
| GRPO fine-tuning | |
| 4B draft model release | Now |
---
## Technical Requirements
* **GPU**: ~4GB VRAM for 4B inference on GGUF.
* **Libraries**: `transformers`, `torch`, `peft`.
* Compatible with Hugging Face inference APIs and local generation pipelines.
---
## Community & Contribution
* **Join our Discord:** [https://discord.gg/GNbWAeJ4](https://discord.gg/GNbWAeJ4)
* Chat about AI, design, or model training.
* Want to contribute UIs or feedback? Lets talk!
---
## Citation
```bibtex
@misc{tesslate_UIGEN-T3,
title={UIGEN-T3: Hybrid Reasoning for Robust UI Generation on Qwen3},
author={Tesslate Team},
year={2025},
publisher={Tesslate},
note={Non-commercial Research License},
url={https://huggingface.co/tesslate/UIGEN-T3}
}