Update Dockerfile

Dockerfile

@@ -1,24 +1,11 @@
 FROM ghcr.io/ggml-org/llama.cpp:full
 
-# Install wget and other dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    wget \
-    && rm -rf /var/lib/apt/lists/*
+RUN apt update && apt install wget -y
+
+RUN wget "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf" -O /qwen2.5-coder-7b-instruct-q4_k_m.gguf
+
+CMD ["--server", "-m", "/qwen2.5-coder-7b-instruct-q4_k_m.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512"]
+
 
-# Download the specific GGUF file (not the HTML page)
-# Using Q4_K_M for optimal balance on free tier (2 vCPU, 16GB RAM)
-RUN wget --no-check-certificate "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf" \
-    -O /model.gguf
 
-# Expose Hugging Face Spaces default port
-EXPOSE 7860
 
-# Run llama.cpp server with optimized settings for free tier
-ENTRYPOINT ["/llama-server"]
-CMD ["-m", "/model.gguf", \
-     "--port", "7860", \
-     "--host", "0.0.0.0", \
-     "-c", "4096", \
-     "-n", "512", \
-     "--threads", "2", \
-     "--threads-batch", "2"]