Update Dockerfile

Dockerfile

@@ -4,52 +4,29 @@ WORKDIR /app
 
 # Install Python
 RUN apt-get update && \
-    apt-get install -y python3 python3-pip python3-venv && \
+    apt-get install -y --no-install-recommends \
+        python3 \
+        python3-pip \
+        python3-venv && \
     rm -rf /var/lib/apt/lists/*
 
+# Python Virtual Environment
 RUN python3 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
+ENV PATH="/opt/venv/bin:${PATH}"
 
-# Install HuggingFace Hub
-RUN pip install --no-cache-dir -U pip huggingface_hub
+# Install Hugging Face Hub
+RUN pip install --no-cache-dir --upgrade pip huggingface_hub
 
-# Download Model
-RUN python3 -c "from huggingface_hub import hf_hub_download; \
-hf_hub_download( \
-repo_id='Qwen/Qwen2.5-Coder-3B-Instruct-GGUF', \
-filename='qwen2.5-coder-3b-instruct-q4_k_m.gguf', \
-local_dir='/app')"
+# Download model during image build
+RUN python3 - <<'PY'
+from huggingface_hub import hf_hub_download
 
-CMD [
-"--server",
+hf_hub_download(
+    repo_id="Qwen/Qwen2.5-Coder-3B-Instruct-GGUF",
+    filename="qwen2.5-coder-3b-instruct-q4_k_m.gguf",
+    local_dir="/app"
+)
+PY
 
-"-m",
-"/app/qwen2.5-coder-3b-instruct-q4_k_m.gguf",
-
-"--host",
-"0.0.0.0",
-
-"--port",
-"7860",
-
-"-t",
-"4",
-
-"-b",
-"1024",
-
-"-c",
-"16384",
-
-"-n",
-"4096",
-
-"--parallel",
-"1",
-
-"--cache-type-k",
-"q8_0",
-
-"--cache-type-v",
-"q8_0"
-]
+# llama.cpp arguments
+CMD ["--server","-m","/app/qwen2.5-coder-3b-instruct-q4_k_m.gguf","--host","0.0.0.0","--port","7860","-t","4","-b","1024","-c","16384","-n","4096","--parallel","1","--cache-type-k","q8_0","--cache-type-v","q8_0"]