Update Dockerfile

Dockerfile

@@ -2,25 +2,51 @@ FROM ubuntu:24.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 
+# Install dependencies
 RUN apt-get update && \
-    apt-get install -y git build-essential cmake python3 python3-pip curl && \
+    apt-get install -y \
+    git \
+    build-essential \
+    cmake \
+    python3 \
+    python3-pip \
+    python3-venv \
+    curl && \
     rm -rf /var/lib/apt/lists/*
 
+# Create Python virtual environment
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Upgrade pip
+RUN pip install --upgrade pip
+
+# Install Hugging Face Hub
+RUN pip install --no-cache-dir huggingface_hub
+
+# Working directory
 WORKDIR /app
 
+# Clone llama.cpp
 RUN git clone https://github.com/ggml-org/llama.cpp.git
 
+# Build llama.cpp
 WORKDIR /app/llama.cpp
 
 RUN cmake -B build
-RUN cmake --build build -j4
 
-WORKDIR /app
+RUN cmake --build build -j$(nproc)
 
-RUN pip3 install --no-cache-dir huggingface_hub
+# Download GGUF model
+WORKDIR /app
 
-RUN python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF', filename='Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf', local_dir='/app/model')"
+RUN python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF', filename='Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf', local_dir='/app/model')"
 
 EXPOSE 7860
 
-CMD ["/app/llama.cpp/build/bin/llama-server","-m","/app/model/Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf","--host","0.0.0.0","--port","7860","-c","32768","-ngl","0"]
+CMD ["/app/llama.cpp/build/bin/llama-server", \
+"-m", "/app/model/Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf", \
+"--host", "0.0.0.0", \
+"--port", "7860", \
+"-c", "32768", \
+"-ngl", "0"]