Update Dockerfile

Dockerfile

@@ -3,38 +3,24 @@ FROM ubuntu:24.04
 ENV DEBIAN_FRONTEND=noninteractive
 
 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 curl && \
     rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
-# Build latest llama.cpp
-RUN git clone https://github.com/ggml-org/llama.cpp.git && \
-    cd llama.cpp && \
-    cmake -B build && \
-    cmake --build build -j$(nproc)
+RUN git clone https://github.com/ggml-org/llama.cpp.git
+
+WORKDIR /app/llama.cpp
+
+RUN cmake -B build
+RUN cmake --build build -j4
+
+WORKDIR /app
 
 RUN pip3 install --no-cache-dir huggingface_hub
 
-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 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')"
 
 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"]