Update Dockerfile

Dockerfile

@@ -2,14 +2,7 @@ FROM ghcr.io/ggml-org/llama.cpp:full
 
 RUN apt update && apt install wget -y
 
-# Download model
 RUN wget "https://huggingface.co/unsloth/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it-Q4_K_M.gguf" -O /model.gguf
 
-# API-optimized settings: larger context, GPU offload, flash attention
-CMD ["--server", "-m", "/model.gguf", "--port", "7860", "--host", "0.0.0.0", 
-     "-c", "4096",           # Context size: 4K tokens
-     "-n", "1024",           # Max generation: 1K tokens  
-     "-ngl", "999",          # Offload all layers to GPU (if available)
-     "-fa",                  # Flash Attention for speed
-     "--chat-template", "gemma",  # Proper chat formatting
-     "--timeout", "300"]     # 5 min timeout for long requests
+# Single line CMD - no comments inside
+CMD ["--server", "-m", "/model.gguf", "--port", "7860", "--host", "0.0.0.0", "-c", "4096", "-n", "1024", "-ngl", "999", "-fa", "--chat-template", "gemma"]