Create README.md

README.md

@@ -0,0 +1,26 @@
+---
+title: CogVLM (4-bit) - Free Tier
+emoji: 🖼️
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: "4.0.0"
+app_file: app.py
+pinned: false
+---
+
+# CogVLM (4-bit Quantized) - Free Tier Compatible
+This Space runs a quantized **CogVLM (4-bit)** model for vision-language tasks.
+
+## 🚀 Features
+- **Supports Image & Text inputs**
+- **Runs on Hugging Face Free Tier (T4 GPU)**
+- **Quantized to 4-bit for efficiency**
+
+## ⚡ Usage
+Upload an image and ask a question. The model will generate a response.
+
+> **Note:** This model requires a **T4 GPU** on Hugging Face Spaces. If it crashes, try using a smaller alternative like **BLIP-2**.
+
+### **📜 License**
+This model follows the **THUDM/CogVLM** licensing terms.