|
--- |
|
license: mit |
|
language: |
|
- en |
|
base_model: |
|
- Tesslate/UIGEN-T2-7B |
|
pipeline_tag: text-generation |
|
library_name: transformers |
|
tags: |
|
- PEFT |
|
- Qwen2 |
|
- UI-Generation |
|
- tailwind-css |
|
- html |
|
--- |
|
# Tesslate/UIGEN-T2-7B (GGUF Q4) - Sandlogic Lexicons |
|
|
|
## Model Overview |
|
|
|
**UIGEN-T2-7B** is the latest innovation in the UIGEN model series by Tesslate, engineered specifically for high-quality, design-aware user interface (UI) code generation. Built on the strong foundation of the **Qwen2.5-Coder-7B-Instruct** model and fine-tuned using **PEFT/LoRA** (Rank 128), UIGEN-T2 has been trained on a significantly larger dataset of **50,000 annotated UI samples**. This enables it to generate not only functional HTML and Tailwind CSS code but also code that aligns with usability, design structure, and modern layout principles. |
|
|
|
## Model Highlights |
|
|
|
- **Architecture**: Based on Qwen2.5-Coder-7B-Instruct (decoder-only transformer) |
|
- **Quantization Format**: GGUF Q4 |
|
- **LoRA Fine-Tuning**: PEFT/LoRA (Rank 128), with checkpoints published at each training stage |
|
- **Training Dataset**: 50,000 high-quality UI examples (up from 400 in the previous version) |
|
- **Code Output**: Semantic HTML and utility-first Tailwind CSS |
|
- **UI-Based Reasoning**: Incorporates guidance from a reasoning teacher model to ensure usability and aesthetics |
|
- **Chat Interface**: Improved prompt interaction for seamless developer experience |
|
|
|
## Intended Use Cases |
|
|
|
### Recommended Applications |
|
|
|
- **Rapid UI Prototyping** |
|
Generate clean, production-ready HTML/Tailwind code from natural language descriptions or wireframes. |
|
|
|
- **Component Generation** |
|
Create both standard (buttons, forms, cards) and custom components based on user-defined design goals. |
|
|
|
- **Frontend Development Assistant** |
|
Accelerate development by producing baseline layouts and component structures for web interfaces. |
|
|
|
- **Design-to-Code Exploration** |
|
Bridge the gap between visual design and code implementation, especially helpful for non-developers or design teams. |
|
|
|
## Model Integration |
|
|
|
This quantized **Q4 GGUF** version of UIGEN-T2-7B is now part of the [Sandlogic Lexicons](https://huggingface.co/SandLogicTechnologies) model zoo. It is optimized for efficient inference on edge and constrained environments, without compromising on code quality or reasoning capability. |
|
|
|
|
|
|
|
|