Create README.md

README.md

@@ -1,15 +1,58 @@
 ---
 title: Llama 3.2 1B Codex
-emoji: 🦀
-colorFrom: pink
-colorTo: purple
+emoji: 🤖
+colorFrom: purple
+colorTo: blue
 sdk: gradio
-sdk_version: 6.14.0
-python_version: '3.13'
+sdk_version: 4.0.0
 app_file: app.py
 pinned: false
-license: apache-2.0
-short_description: 'Testing publicly my finetune of Llama 3.2 1B '
+license: llama3.2
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🤖 Llama 3.2 1B Codex
+
+## AI Coding Assistant with Thinking Mode
+
+This Space hosts **Llama-3.2-1B-Codex**, a fine-tuned version of Meta's Llama 3.2 1B Instruct model specialized for code generation with explicit reasoning capabilities.
+
+### Features
+
+- 🧠 **Thinking Mode**: Model shows its reasoning process before writing code
+- ⚡ **Fast Mode**: Direct code generation for simple tasks
+- 💻 **Multi-language Support**: Python, JavaScript, Java, C++, and more
+- 🔍 **Chain-of-Thought**: Alternative reasoning strategy for complex problems
+- 🎛️ **Adjustable Parameters**: Control creativity and response length
+
+### How to Use
+
+1. Type your coding question in the chat box
+2. Enable/disable Thinking Mode based on task complexity
+3. Adjust temperature for creative vs precise responses
+4. Get code with explanations!
+
+### Examples
+
+- "Write a Python function to find the longest common prefix"
+- "Implement a binary search tree with insert and search"
+- "Create a decorator that measures function execution time"
+- "Explain recursion with a practical example"
+
+### Built With
+
+- **Base Model**: Meta Llama 3.2 1B Instruct
+- **Fine-tuned on**: Code datasets (The Stack, StarCoderData, CodeFeedback)
+- **Framework**: Transformers + PEFT + Gradio
+
+### License
+
+This model is governed by the **Llama 3.2 Community License**. 
+See [LICENSE.txt](./LICENSE.txt) for full terms.
+
+### Attribution
+
+Built with Llama - Meta's open-source AI model.
+
+---
+
+*Fast, thoughtful code assistance for developers*