Update README.md

README.md

@@ -1,64 +1,22 @@
-# 📝 Handwritten Polynomial Solver
-
-This Hugging Face Space fine-tunes a Pix2Tex-style architecture using TrOCR on the [Azu/Handwritten-Mathematical-Expression-Convert-LaTeX](https://huggingface.co/datasets/Azu/Handwritten-Mathematical-Expression-Convert-LaTeX) dataset (~12K labeled handwritten math expressions). It then uses the trained model to extract LaTeX from user-uploaded images and solve polynomial equations step-by-step.
-
----
-
-## 🚀 How to Use
-
-### 🔧 Phase 1: Train the OCR Model
-
-1. Rename:
-   - `app.py` → `app_ui.py`
-   - `train.py` → `app.py`
-
-2. Rebuild the Space (top-right corner ➜ "Runtime ➜ Restart & Run All").
-
-3. Wait for training to finish (~10–20 min). A `trained_model/` directory will be saved.
-
 ---
-
-### 🎨 Phase 2: Run the UI
-
-1. Rename:
-   - `app_ui.py` → `app.py`
-   - `app.py` (the old training script) → `train.py` (optional)
-
-2. Rebuild again.
-
-3. Upload a handwritten math image (like `x^3 + 3x - 2 = 0`), and it will:
-   - Extract LaTeX
-   - Clean & standardize
-   - Parse and simplify
-   - Solve and show roots step-by-step
-
+title: "Handwritten Polynomial Solver"
+emoji: "🧠"
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: "3.0"
+app_file: app.py
+pinned: false
 ---
 
-## 💻 Notes
+# Handwritten Polynomial Solver
 
-- **CPU-only**: Designed to work in free CPU-only Spaces.
-- **Training config**:
-  - Samples: 1,000 (you can increase later)
-  - Batch size: 2
-  - Epochs: 1
-- Based on `microsoft/trocr-base-handwritten` for OCR.
+This Space fine-tunes Pix2Tex on the Azu/Handwritten‑Mathematical‑Expression‑Convert‑LaTeX dataset (~12K handwritten math samples).
 
----
-
-## 📦 Files
+## 🚀 Usage
 
-| File         | Purpose                              |
-|--------------|--------------------------------------|
-| `app.py`     | Gradio UI (after training is done)   |
-| `train.py`   | Trains the model                     |
-| `model.py`   | OCR wrapper for inference            |
-| `requirements.txt` | Python dependencies             |
-
----
+- **Train the model:** Rename `app.py → app_ui.py` and `train.py → app.py`, then rebuild the Space.  
+- **Switch to UI:** Once you see `trained_model/`, rename back (`app.py → train.py`, `app_ui.py → app.py`) and rebuild.  
 
-## ✅ Status
 
-- [x] Handwritten OCR
-- [x] Step-by-step solving
-- [x] Fine-tuning on real handwritten dataset