Update Dockerfile

Dockerfile

@@ -1,26 +1,17 @@
-FROM ubuntu:24.04
+FROM ghcr.io/ggml-org/llama.cpp:server
 
-RUN apt-get update && apt-get install -y \
-    build-essential cmake git curl \
-    libopenblas-dev
+ENV HOME=/tmp
 
-RUN git clone https://github.com/ggml-org/llama.cpp /app
-WORKDIR /app
-RUN cmake -B build \
-    -DGGML_BLAS=ON \
-    -DGGML_BLAS_VENDOR=OpenBLAS \
-    -DCMAKE_BUILD_TYPE=Release \
-    && cmake --build build --target llama-server -j$(nproc)
+RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
 
-RUN curl -L -o model.gguf \
-    "https://huggingface.co/Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned/resolve/main/LFM2.5-1.2B-Instruct-roleplay-tuned.Q8_0.gguf"
+RUN curl -L -o /model.gguf \
+  "https://huggingface.co/Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned/resolve/main/LFM2.5-1.2B-Instruct-roleplay-tuned.Q8_0.gguf"
 
 EXPOSE 7860
 
-CMD ["./build/bin/llama-server", \
-     "-m", "model.gguf", \
+CMD ["-m", "/model.gguf", \
      "--host", "0.0.0.0", \
      "--port", "7860", \
      "-c", "32768", \
      "--threads", "2", \
-     "--flash-attn", "on"]
+     "--flash-attn"]