Update README.md

README.md

@@ -1,50 +1,25 @@
 ---
-title: Veda Programming LLM
+title: Veda Programming Assistant
 emoji: 🕉️
 colorFrom: purple
-colorTo: blue
+colorTo: indigo
 sdk: gradio
-sdk_version: 3.50.0
+sdk_version: 6.2.0
 app_file: app.py
 pinned: false
-license: mit
 ---
 
-# 🕉️ Veda Programming LLM
+# Veda Programming Assistant
 
-A TensorFlow-based Large Language Model for programming code generation.
+A conversational AI assistant for programming that can:
+- Chat naturally about programming
+- Write Python code
+- Explain programming concepts
+- Answer questions
+- Learn from user feedback
 
 ## Features
-
-- **Code Generation**: Generate Python code from prompts
-- **Custom Training**: Train on your own code samples
-- **Transformer Architecture**: Uses modern transformer blocks
-- **Interactive Interface**: Easy-to-use Gradio interface
-
-## Model Architecture
-
-- Transformer-based decoder architecture
-- Configurable model sizes (small/medium/large)
-- Causal attention masking for autoregressive generation
-- Custom tokenizer optimized for code
-
-## Usage
-
-1. **Generate Code**: Enter a code prompt and adjust generation parameters
-2. **Train Model**: Paste your code samples and train the model
-3. **View Model Info**: Check model architecture and parameters
-
-## Parameters
-
-- **Temperature**: Controls randomness (lower = more deterministic)
-- **Top-K**: Limits sampling to top K tokens
-- **Top-P**: Nucleus sampling threshold
-- **Max Tokens**: Maximum number of tokens to generate
-
-## Training Data
-
-The model can be trained on `programming.txt` containing Python code samples.
-
-## License
-
-MIT License
+- Transformer-based language model
+- Conversation memory
+- Continuous learning from feedback
+- Code generation with syntax highlighting