jinxsuperdev commited on
Commit
650b184
·
verified ·
1 Parent(s): 7490e87

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -3
README.md CHANGED
@@ -1,3 +1,59 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - id
6
+ tags:
7
+ - code
8
+ - nextjs
9
+ - typescript
10
+ - react
11
+ - unsloth
12
+ - web-design
13
+ ---
14
+
15
+ # Gwen 1.0 Code Mini
16
+
17
+ ![Gwen 1.0 Banner](Screenshot 2026-05-02 111143.png)
18
+
19
+ **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.
20
+
21
+ ## Model Details
22
+
23
+ ### Model Description
24
+
25
+ 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.
26
+
27
+ - **Developed by:** JinXSuper
28
+ - **Model type:** Causal Language Model (Fine-tuned for Web Development)
29
+ - **Language(s) (NLP):** English, Indonesian (Natural Mix)
30
+ - **License:** apache-2.0
31
+ - **Finetuned from model:** Qwen Series
32
+
33
+ ## Uses
34
+
35
+ ### Direct Use
36
+
37
+ Gwen 1.0 Code Mini is intended for:
38
+ * Building modern web interfaces using **React 19** and **Next.js 15/16**.
39
+ * Styling with **Tailwind CSS v4** and implementing **shadcn/ui** components.
40
+ * Integrating motion libraries like **GSAP**, **Framer Motion**, and **Lenis**.
41
+
42
+ ### Out-of-Scope Use
43
+
44
+ * Low-level system programming (C, Rust, or Assembly).
45
+ * Non-technical creative writing or general-purpose tasks outside of coding.
46
+
47
+ ## Bias, Risks, and Limitations
48
+
49
+ 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.
50
+
51
+ ## How to Get Started with the Model
52
+
53
+ You can load the model using the following snippet:
54
+ ```python
55
+ from transformers import AutoModelForCausalLM, AutoTokenizer
56
+
57
+ model_id = "jinxsuperdev/gwen1.0-code-mini"
58
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
59
+ model = AutoModelForCausalLM.from_pretrained(model_id)