Update LLM

Dockerfile

@@ -6,6 +6,10 @@ USER user
 ENV HOME=/home/user
 ENV PATH=/home/user/.local/bin:$PATH
 
+WORKDIR /app
+
+ADD --chown=user https://huggingface.co/unsloth/gemma-3n-E4B-it-GGUF/resolve/main/gemma-3n-E4B-it-UD-Q4_K_XL.gguf /app/model.gguf
+
 EXPOSE 7860
 
-CMD ["--port", "7860", "--no-mmap", "--flash-attn", "on", "--fit", "on", "--ctx-size", "8192", "--samplers", "min_p", "--min-p", "0.005", "--backend-sampling", "--webui-mcp-proxy", "-hf", "Intel/Qwen3-Coder-30B-A3B-Instruct-gguf-q2ks-mixed-AutoRound:Q2_K_S", "--chat-template-kwargs", "{ \"enable_thinking\": false }"]
+CMD ["--port", "7860", "--no-mmap", "--flash-attn", "on", "--fit", "on", "--ctx-size", "8192", "--samplers", "min_p", "--min-p", "0.005", "--backend-sampling", "--webui-mcp-proxy", "-m", "/app/model.gguf", "--chat-template-kwargs", "{ \"enable_thinking\": false }"]