Update README.md

README.md

@@ -29,31 +29,31 @@ pipeline_tag: image-text-to-text
 [![Language](https://img.shields.io/badge/Language-ID%20%7C%20EN-green)](https://huggingface.co/kadalicious22/snapgate-VL-4B)
 [![Website](https://img.shields.io/badge/Website-snapgate.tech-purple)](https://snapgate.tech)
 
-**snapgate-code-4B** adalah model vision-language multimodal hasil fine-tuning dari [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) menggunakan **QLoRA**, dioptimalkan khusus untuk kebutuhan **developer** dan **desainer** — memahami gambar sekaligus teks dengan presisi tinggi.
+**snapgate-code-4B** is a multimodal vision-language model fine-tuned from [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) using **QLoRA**, specifically optimized for **developers** and **designers** — understanding both images and text with high precision.
 
-*Dikembangkan oleh [Snapgate](https://snapgate.tech) · Made with ❤️ in Indonesia 🇮🇩*
+*Developed by [Snapgate](https://snapgate.tech) · Made with ❤️ in Indonesia 🇮🇩*
 
 </div>
 
 ---
 
-## 🧠 Kemampuan Utama
+## 🧠 Core Capabilities
 
-| Kemampuan | Deskripsi |
+| Capability | Description |
 |-----------|-----------|
-| 💻 **Code Generation & Review** | Menulis, menganalisis, debug, dan mengoptimalkan kode (Python, JS, TS, HTML/CSS, SQL, dll.) |
-| 🎨 **UI/UX Design Analysis** | Menganalisis screenshot antarmuka, memberikan saran desain, mengidentifikasi masalah UX |
-| 🖼️ **Design to Code** | Mengkonversi mockup, wireframe, atau screenshot UI menjadi kode HTML/CSS/React/Tailwind |
-| 🏗️ **Diagram & Architecture** | Memahami diagram alur, arsitektur sistem, ERD, dan flowchart teknis |
-| 📸 **Code from Image** | Membaca dan menjelaskan kode dari screenshot atau foto |
-| 📝 **Technical Documentation** | Membuat dokumentasi teknis yang jelas, terstruktur, dan profesional |
+| 💻 **Code Generation & Review** | Write, analyze, debug, and optimize code (Python, JS, TS, HTML/CSS, SQL, etc.) |
+| 🎨 **UI/UX Design Analysis** | Analyze interface screenshots, provide design suggestions, identify UX issues |
+| 🖼️ **Design to Code** | Convert mockups, wireframes, or UI screenshots into HTML/CSS/React/Tailwind code |
+| 🏗️ **Diagram & Architecture** | Understand flowcharts, system architecture, ERDs, and technical diagrams |
+| 📸 **Code from Image** | Read and explain code from screenshots or photos |
+| 📝 **Technical Documentation** | Generate clear, structured, and professional technical documentation |
 
 ---
 
 ## 🔧 Training Configuration
 
 <details>
-<summary><b>Klik untuk lihat detail training</b></summary>
+<summary><b>Click to view training details</b></summary>
 
 | Parameter | Value |
 |-----------|-------|
@@ -71,10 +71,10 @@ pipeline_tag: image-text-to-text
 | 🎛️ Precision | `bfloat16` |
 | 🖥️ Hardware | NVIDIA T4 · Google Colab |
 | 📦 Dataset | 200 samples internal Snapgate |
-| 🏷️ Kategori | 10 kategori · 20 samples each |
+| 🏷️ Categories | 10 categories · 20 samples each |
 | 📊 Format | ShareGPT |
 
-**Kategori Dataset:**
+**Dataset Categories:**
 `code_generation` · `code_review` · `debugging` · `refactoring` · `ui_html_css` · `ui_react` · `ui_tailwind` · `design_system` · `ux_analysis` · `design_to_code`
 
 </details>
@@ -83,7 +83,7 @@ pipeline_tag: image-text-to-text
 
 ## 📊 Training Progress
 
-Loss turun konsisten selama training — dari **1.242 → 0.444** ✅
+Loss decreased consistently throughout training — from **1.242 → 0.444** ✅
 
 ```
 Step  5  │███░░░░░░░░░░░░░░░░░│  Loss: 1.242
@@ -105,7 +105,7 @@ Step 75  │██████████████░░░░░░│  Los
 
 ---
 
-## 🚀 Cara Penggunaan
+## 🚀 Usage
 
 ### 1. Install Dependencies
 
@@ -129,11 +129,11 @@ model = Qwen3VLForConditionalGeneration.from_pretrained(
     trust_remote_code=True,
 )
 
-SYSTEM_PROMPT = """Kamu adalah Snapgate AI, asisten AI multimodal milik Snapgate \
-yang ahli dalam bidang coding dan UI/UX design."""
+SYSTEM_PROMPT = """You are Snapgate AI, a multimodal AI assistant by Snapgate \
+specialized in coding and UI/UX design."""
 ```
 
-### 3. Inference dengan Gambar
+### 3. Inference with Image
 
 ```python
 from qwen_vl_utils import process_vision_info
@@ -144,7 +144,7 @@ messages = [
         "role": "user",
         "content": [
             {"type": "image", "image": "path/to/your/image.png"},
-            {"type": "text", "text": "Analisis UI dari gambar ini dan buat kode HTML/CSS-nya."},
+            {"type": "text", "text": "Analyze the UI from this image and generate its HTML/CSS code."},
         ],
     },
 ]
@@ -166,12 +166,12 @@ response = processor.batch_decode(generated, skip_special_tokens=True)[0]
 print(response)
 ```
 
-### 4. Inference Teks Saja
+### 4. Text-Only Inference
 
 ```python
 messages = [
     {"role": "system", "content": SYSTEM_PROMPT},
-    {"role": "user", "content": "Buatkan fungsi Python untuk validasi email dengan regex."},
+    {"role": "user", "content": "Write a Python function to validate email using regex."},
 ]
 
 text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
@@ -189,18 +189,18 @@ print(response)
 
 ---
 
-## ⚠️ Limitasi
+## ⚠️ Limitations
 
-- 📦 Di-training pada dataset internal Snapgate yang relatif kecil (200 samples) — performa akan terus meningkat seiring penambahan data
-- 🌏 Dioptimalkan untuk Bahasa Indonesia dan Inggris; bahasa lain belum diuji
-- 🎯 Performa terbaik pada task coding dan UI analysis; kurang optimal untuk domain di luar itu (misal: sains, hukum, medis)
-- 🖥️ Direkomendasikan minimal GPU dengan 8GB VRAM untuk inference yang nyaman
+- 📦 Trained on a relatively small internal Snapgate dataset (200 samples) — performance will improve as more data is added
+- 🌏 Optimized for Indonesian and English; other languages have not been tested
+- 🎯 Best performance on coding and UI analysis tasks; less optimal for other domains (e.g., science, law, medicine)
+- 🖥️ A GPU with at least 8GB VRAM is recommended for comfortable inference
 
 ---
 
-## 📄 Lisensi
+## 📄 License
 
-Dirilis di bawah lisensi **Apache 2.0**, mengikuti lisensi base model [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct).
+Released under the **Apache 2.0** license, following the base model license of [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct).
 
 ---
 
@@ -210,7 +210,6 @@ Dirilis di bawah lisensi **Apache 2.0**, mengikuti lisensi base model [Qwen3-VL-
 |---|---|
 | 🌐 Website | [snapgate.tech](https://snapgate.tech) |
 | 🤗 Base Model | [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) |
-| 📧 Contact | Via website Snapgate |
-
----
+| 📧 Contact | Via Snapgate website |
 
+---