Update entrypoint.sh

entrypoint.sh

@@ -1,46 +1,17 @@
 #!/bin/bash
+set -e
 
-echo "============================================"
-echo "🔥 GOD CODING MACHINE - Docker Edition"
-echo "   18GB RAM | CPU | No Rate Limits!"
-echo "============================================"
-echo ""
-
-# Start Ollama in background
-echo "🚀 Starting Ollama server..."
+echo "Starting Ollama..."
 ollama serve &
 
-# Wait for Ollama to be ready
-echo "⏳ Waiting for Ollama..."
-for i in {1..60}; do
-    if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
-        echo "✅ Ollama is ready!"
-        break
-    fi
-    sleep 1
-done
-
-# Pull models optimized for 18GB RAM + CPU
-echo ""
-echo "📦 Downloading models (first run takes ~5-10 min)..."
-echo ""
-
-# Main model - Qwen 2.5 Coder 7B (best quality for our RAM)
-echo "📥 Pulling Qwen2.5-Coder:7b (main model)..."
-ollama pull qwen2.5-coder:7b
+echo "Waiting for Ollama to start..."
+sleep 10
 
-# Smaller fast model for quick tasks
-echo "📥 Pulling Qwen2.5-Coder:3b (fast model)..."
+echo "Pulling models..."
 ollama pull qwen2.5-coder:3b
 
-echo ""
-echo "============================================"
-echo "✅ All models ready!"
-echo "============================================"
+echo "Models ready!"
 ollama list
-echo ""
-echo "🌐 Starting Gradio interface..."
-echo ""
 
-# Start the Gradio app
-python app.py
+echo "Starting Gradio..."
+python app.py