Add Dockerfile and README config for Hugging Face Space

Dockerfile

@@ -1,12 +1,8 @@
-FROM debian:bookworm-slim
+FROM ghcr.io/ggerganov/llama.cpp:server
 
-ARG DEBIAN_FRONTEND=noninteractive
-RUN apt-get update && apt-get install -y --no-install-recommends git build-essential cmake python3 python3-pip curl ca-certificates pkg-config libcurl4-openssl-dev && rm -rf /var/lib/apt/lists/*
+ENV MODEL_URL="https://huggingface.co/bartowski/Qwen2.5-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf"
 
-WORKDIR /app
-RUN git clone --depth 1 https://github.com/ggerganov/llama.cpp.git && cd llama.cpp && mkdir build && cd build && cmake -DGGML_NATIVE=ON -DLLAMA_BUILD_SERVER=ON .. && cmake --build . -j
-
-RUN mkdir -p /models && curl -L -o /models/model.gguf https://huggingface.co/bartowski/Qwen2.5-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf
+RUN mkdir -p /models && curl -L -o /models/model.gguf %MODEL_URL%
 
 EXPOSE 7860
-CMD ["bash","-lc","/app/llama.cpp/build/bin/llama-server -m /models/model.gguf -c 2048 -ngl 0 -t 4 --host 0.0.0.0 --port 7860"]
+CMD ["llama-server", "-m", "/models/model.gguf", "-c", "2048", "-ngl", "0", "-t", "4", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,7 +1,8 @@
---- 
-title: Llama.cpp Tiny (Docker) 
-sdk: docker 
-app_port: 7860 
---- 
-
-Tiny llama.cpp server on CPU using Qwen2.5-0.5B-Instruct (Q4_K_M).
+---
+title: Llama.cpp Tiny
+colorFrom: gray
+colorTo: blue
+sdk: docker
+app_port: 7860
+pinned: false
+---