| --- |
| license: apache-2.0 |
| language: |
| - en |
| - id |
| tags: |
| - code |
| - nextjs |
| - typescript |
| - react |
| - unsloth |
| - web-design |
| --- |
| |
| # Gwen 1.0 Code Mini |
|
|
|  |
|
|
| **Gwen 1.0 Code Mini** is an elegant, high-efficiency AI coding assistant specialized in modern web development stacks. It is designed to be sharp, loyal, and highly effective for developers working with the Vercel ecosystem. |
|
|
| ## Model Details |
|
|
| ### Model Description |
|
|
| Gwen 1.0 Code Mini is the lightweight variant of the Gwen series, optimized for speed and efficiency without sacrificing the "sharp" reasoning required for complex UI/UX tasks. It excels in generating clean, minimalist code following the Geist Design System. |
|
|
| - **Developed by:** JinXSuper |
| - **Model type:** Causal Language Model (Fine-tuned for Web Development) |
| - **Language(s) (NLP):** English, Indonesian (Natural Mix) |
| - **License:** apache-2.0 |
| - **Finetuned from model:** Qwen Series |
|
|
| ## Uses |
|
|
| ### Direct Use |
|
|
| Gwen 1.0 Code Mini is intended for: |
| * Building modern web interfaces using **React 19** and **Next.js 15/16**. |
| * Styling with **Tailwind CSS v4** and implementing **shadcn/ui** components. |
| * Integrating motion libraries like **GSAP**, **Framer Motion**, and **Lenis**. |
|
|
| ### Out-of-Scope Use |
|
|
| * Low-level system programming (C, Rust, or Assembly). |
| * Non-technical creative writing or general-purpose tasks outside of coding. |
|
|
| ## Bias, Risks, and Limitations |
|
|
| Gwen 1.0 is heavily biased towards minimalist, high-contrast aesthetics and the **Vercel** design philosophy. It may prioritize "sharp" and "clean" code structures over more verbose legacy patterns. |
|
|
| ## How to Get Started with the Model |
|
|
| You can load the model using the following snippet: |
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model_id = "jinxsuperdev/gwen1.0-code-mini" |
| tokenizer = AutoTokenizer.from_pretrained(model_id) |
| model = AutoModelForCausalLM.from_pretrained(model_id) |
