Update Dockerfile

Dockerfile

@@ -3,17 +3,17 @@ FROM python:3.10-slim
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
     build-essential \
-    wget \
-    && rm -rf /var/lib/apt/lists/*
+        wget \
+            && rm -rf /var/lib/apt/lists/*
 
-# Install llama-cpp-python with server extra
-RUN pip install --no-cache-dir llama-cpp-python[server]
+            # Install llama-cpp-python with server extra using pre-built wheels to avoid timeout
+            RUN pip install llama-cpp-python[server] --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
-# Download the model (Qwen 2.5 7B Instruct Quantized)
-RUN wget https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GGUF/resolve/main/qwen2.5-7b-instruct-q4_k_m.gguf -O model.gguf
+            # Download the model (Qwen 2.5 7B Instruct Quantized)
+            RUN wget https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GGUF/resolve/main/qwen2.5-7b-instruct-q4_k_m.gguf -O model.gguf
 
-# Expose the HF Space port
-EXPOSE 7860
+            # Expose the HF Space port
+            EXPOSE 7860
 
-# Run the OpenAI-compatible server
-CMD ["python3", "-m", "llama_cpp.server", "--model", "model.gguf", "--host", "0.0.0.0", "--port", "7860", "--n_ctx", "4096"]
+            # Run the OpenAI-compatible server
+            CMD ["python3", "-m", "llama_cpp.server", "--model", "model.gguf", "--host", "0.0.0.0", "--port", "7860", "--n_ctx", "4096"]