Add Dockerfile for llama.cpp Space and update README

.dockerignore

@@ -0,0 +1,3 @@
+__pycache__/ 
+*.pyc 
+*.tmp 

Dockerfile

@@ -0,0 +1,12 @@
+FROM debian:bookworm-slim
+
+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/*
+
+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
+
+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"]

README.md

@@ -1,12 +1,7 @@
----
-title: Llamacpp Tiny
-emoji: 🚀
-colorFrom: yellow
-colorTo: blue
-sdk: docker
-pinned: false
-license: apache-2.0
-short_description: a test docker space
----
+--- 
+title: Llama.cpp Tiny (Docker) 
+sdk: docker 
+app_port: 7860 
+--- 
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Tiny llama.cpp server on CPU using Qwen2.5-0.5B-Instruct (Q4_K_M).