Update entrypoint.sh

entrypoint.sh

@@ -1,26 +1,37 @@
 #!/bin/bash
 
-echo "Starting Ollama server..."
-ollama serve &
+echo "🔥 Axon v6 - llama.cpp Edition"
+echo "📥 Downloading models..."
 
-echo "Waiting for Ollama to be ready..."
-while ! curl -s http://localhost:11434/api/tags > /dev/null; do
-    sleep 1
-done
-echo "✅ Ollama is ready!"
+# Create models directory
+mkdir -p /models
 
-echo "📥 Downloading models..."
+# Download GGUFs from HuggingFace
+python3 << 'EOF'
+from huggingface_hub import hf_hub_download
+import os
+
+models = [
+    ("Qwen/Qwen2.5-Coder-7B-Instruct-GGUF", "qwen2.5-coder-7b-instruct-q4_k_m.gguf"),
+    ("Qwen/Qwen2.5-Coder-3B-Instruct-GGUF", "qwen2.5-coder-3b-instruct-q4_k_m.gguf"),
+    ("Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF", "qwen2.5-coder-1.5b-instruct-q4_k_m.gguf"),
+]
 
-ollama pull qwen2.5-coder:1.5b
-ollama pull qwen2.5-coder:3b
-ollama pull qwen2.5-coder:7b
-ollama pull deepseek-coder:1.3b
-ollama pull deepseek-coder:6.7b
-ollama pull starcoder2:3b
-ollama pull codegemma:2b
+for repo, filename in models:
+    print(f"📥 Downloading {filename}...")
+    try:
+        hf_hub_download(
+            repo_id=repo,
+            filename=filename,
+            local_dir="/models",
+            local_dir_use_symlinks=False
+        )
+        print(f"✅ {filename} ready!")
+    except Exception as e:
+        print(f"❌ Failed to download {filename}: {e}")
 
-echo "✅ Models ready!"
-ollama list
+print("✅ All models downloaded!")
+EOF
 
-echo "🚀 Starting App..."
+echo "🚀 Starting Axon..."
 python3 /app.py