Update Dockerfile

Dockerfile

@@ -1,30 +1,25 @@
-FROM python:3.10-slim
-
-# GCC, G++, CMake aur Ninja install karein (Taki llama-cpp bina kisi missing compiler error ke build ho sake)
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential \
-    cmake \
-    ninja-build \
-    libgomp1 \
-    curl \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN useradd -m -u 1000 user
-USER user
-ENV PATH="/home/user/.local/bin:$PATH"
+FROM ghcr.io/ggml-org/llama.cpp:full
 
 WORKDIR /app
 
-# Step 1: Base UI dependencies install karein
-RUN pip install --no-cache-dir gradio huggingface_hub
-
-# Step 2: C++ compiler flag ke sath llama-cpp-python install karein
-# (Pehle pre-built CPU wheel try karega, na milne par local GCC compiler se 100% build kar lega)
-RUN CMAKE_ARGS="-DLLAMA_NATIVE=OFF" pip install --no-cache-dir llama-cpp-python \
-    --extra-index-url https://abetlen.github.io/llama-cpp-python/wheels/cpu
-
-COPY --chown=user . /app
-
-EXPOSE 7860
-
-CMD ["python", "app.py"]
+RUN apt update && apt install -y python3 python3-pip python3-venv
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+RUN pip install -U pip huggingface_hub
+
+RUN python3 -c 'from huggingface_hub import hf_hub_download; \
+    repo="HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive"; \
+    hf_hub_download(repo_id=repo, filename="Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf", local_dir="/app"); \
+    hf_hub_download(repo_id=repo, filename="mmproj-Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-f16.gguf", local_dir="/app")'
+
+CMD ["--server", \
+     "-m", "/app/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf", \
+     "--mmproj", "/app/mmproj-Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-f16.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "7860", \
+     "-t", "2", \
+     "--cache-type-k", "q8_0", \
+     "--cache-type-v", "iq4_nl", \
+     "-c", "8192", \
+     "-n", "4096"]