Update README

README.md

@@ -13,14 +13,16 @@ short_description: AI tutor for math learners
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 ## LearnLoop - AI Tutor for math 🔢💡
-  LearnLoop is a  AI-powered math tutor built with Gradio and SymPy. 
-  It helps users understand mathematical expressions step-by-step, using natural language and intuitive feedback.
+  LearnLoop is a lightweight AI-powered math tutor built with Gradio, SymPy, and Transformers. 
+  It explains mathematical questions at different skill levels and verifies expressions using symbolic computation.
 
 ## Features
 - Step-by-step explanations for math expressions
 - Beginner, Intermediate, and Advanced levels
-- Powered by SymPy, Transformers, and PyTorch
-- Clean, responsive UI with soft visual rhythm
+- Automatic math verification using `SymPy`
+- Powered by Qwen2.5-1.5B-Instruct
+- Clean, responsive UI with soft visual rhythm and microinteractions
+- Keyboard support
 
 
 ## Getting started
@@ -37,16 +39,23 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
 ## Requirements
 See `requirements.txt` for full list
 
-## UI 
-- styled using `gr.HTML()` with embedded CSS
+## Explanation logic
+- Uses Qwen2.5-1.5B-Instruct via HuggingFace Transformers
+- Prompt includes:
+  - System messge to guide tone
+  - Dynamic style string based on level and step-by-step toggle
+  - User question
+- Response is trimmed to remove artifacts
+  
+## UI Design
+- Built with `gr.Blocks()`for modular layout
+- Styled using embedded CSS via `gr.HTML()`
 - `.gradio-container` to add color to the background
-- focuses on clarity, calmness and visual harmony
-
-## Button functionality
-- `Explain` button and `Enter` key triggers the explanation
-- `Reset` button clears input and output areas
-- Buttons styled with hover and focus effects 
-- Buttons lighten slightly on hover for visual feedback
-- On click, they shrink and darken briefly to indicate activation
-- Microinteractions improve clarity and responsiveness
-- Styled via CSS inside `gr.HTML()` blocks
+- Buttons styled with hover, focus and click effects
+- Markdown used for instructions and output display
+
+## Output format
+- Explanation from the model
+- Divider line
+- `SymPy`verification result
+- Status note (e.g. Transformers CPU)