Update Dockerfile

Dockerfile

@@ -1,27 +1,7 @@
-# Use official Python slim image
-FROM python:3.12-slim
+FROM ghcr.io/ggml-org/llama.cpp:full
 
-# Set working directory
-WORKDIR /app
+RUN apt update && apt install wget -y
 
-# Avoid Python buffering issues
-ENV PYTHONUNBUFFERED=1
+RUN wget "https://huggingface.co/unsloth/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it-Q8_0.gguf" -O /gemma-3-1b-it-Q8_0.gguf
 
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    git \
-    curl \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install llama-cpp-python with server extras
-RUN pip install --no-cache-dir "llama-cpp-python[server]>=0.1.81" --verbose
-
-# Copy your model file if needed
-# COPY smollm2-360m-instruct-q8_0.gguf ./models/
-
-# Expose default server port
-EXPOSE 5000
-
-# Run llama-cpp server directly
-CMD ["python", "-m", "llama_cpp.server", "--model", "HuggingFaceTB/SmolLM2-360M-Instruct-GGUF", "--filename", "smollm2-360m-instruct-q8_0.gguf", "--host", "0.0.0.0", "--port", "5000"]
+CMD ["--server", "-m", "/gemma-3-1b-it-Q8_0.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512"]