Update entrypoint.sh

entrypoint.sh

@@ -11,14 +11,24 @@ ollama pull qwen2.5-coder:1.5b
 ollama pull qwen2.5-coder:3b
 ollama pull qwen2.5-coder:7b
 
-echo "Downloading Qwen3-Coder-30B-A3B GGUF (this takes a while)..."
+echo "Downloading Qwen3-Coder-30B-A3B GGUF..."
 mkdir -p /tmp/models
-curl -L -o /tmp/models/qwen3-coder-30b-a3b.gguf \
-    "https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF/resolve/main/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf"
+
+# Use huggingface-cli instead (more reliable)
+pip3 install -q huggingface_hub --break-system-packages
+python3 -c "
+from huggingface_hub import hf_hub_download
+path = hf_hub_download(
+    repo_id='Qwen/Qwen3-Coder-30B-A3B-Instruct-GGUF',
+    filename='qwen3-coder-30b-a3b-instruct-q4_k_m.gguf',
+    local_dir='/tmp/models'
+)
+print(f'Downloaded to: {path}')
+"
 
 echo "Creating Ollama model from GGUF..."
 cat > /tmp/Modelfile << 'EOF'
-FROM /tmp/models/qwen3-coder-30b-a3b.gguf
+FROM /tmp/models/qwen3-coder-30b-a3b-instruct-q4_k_m.gguf
 TEMPLATE """{{- if .System }}<|im_start|>system
 {{ .System }}<|im_end|>
 {{ end }}<|im_start|>user