Create Dockerfile

Dockerfile

@@ -0,0 +1,45 @@
+# Using a standard Ubuntu base image
+FROM ubuntu:22.04
+
+# Environment variables
+ENV CACHE_SIZE=16000
+ENV MODEL_NAME="Qwen-7B-gguf"
+ENV MODEL_FILE="qwen7b-q4_0.gguf"
+ENV MODEL_USER="MatrixStudio"
+ENV DEFAULT_MODEL_BRANCH="main"
+ENV MODEL_URL="https://huggingface.co/${MODEL_USER}/${MODEL_NAME}/resolve/${DEFAULT_MODEL_BRANCH}/${MODEL_FILE}"
+
+# Installing necessary packages
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y build-essential python3 python3-pip wget curl git \
+    --no-install-recommends \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Setting up the working directory
+WORKDIR /app
+
+# Cloning the llama.cpp repository
+RUN git clone https://github.com/ggerganov/llama.cpp.git
+
+# Moving to the llama.cpp directory and building the project
+WORKDIR /app/llama.cpp
+RUN make
+
+# List contents to verify the location of the server executable
+RUN ls -la
+
+# Model download process
+RUN mkdir -p models/7B && \
+    wget -O models/7B/${MODEL_FILE} ${MODEL_URL}
+
+# Changing ownership to a non-root user
+RUN useradd -m -u 1000 user && chown -R user:user /app
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Setting up the application
+EXPOSE 8080
+
+# Adjust the CMD to use the absolute path of the server executable
+CMD ["/app/llama.cpp/server", "-m", "/app/llama.cpp/models/7B/${MODEL_FILE}", "-c", "16000"]