Update Dockerfile

Dockerfile

@@ -7,9 +7,12 @@ RUN apt-get update && apt-get install -y wget && rm -rf /var/lib/apt/lists/*
 # Set working directory
 WORKDIR /app
 
-# Install llama-cpp-python with pre-built CPU wheels
+# --- REPLACED SECTION START ---
+# Install llama-cpp-python[server] from the official CPU wheel index
 RUN pip install --no-cache-dir \
-    "llama-cpp-python[server] @ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.90/llama_cpp_python-0.2.90-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl"
+    llama-cpp-python[server] \
+    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+# --- REPLACED SECTION END ---
 
 # Download the Qwen 2.5 Coder GGUF model
 RUN wget https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf
@@ -18,8 +21,6 @@ RUN wget https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main
 EXPOSE 7860
 
 # Run the server
-# --n_threads 2 (HF Free tier has 2 vCPUs)
-# --host 0.0.0.0 --port 7860 (Required for HF)
 CMD ["python3", "-m", "llama_cpp.server", \
      "--model", "qwen2.5-coder-7b-instruct-q4_k_m.gguf", \
      "--host", "0.0.0.0", \