Update Dockerfile

Dockerfile

@@ -1,11 +1,13 @@
 FROM ghcr.io/ggml-org/llama.cpp:server
 
+
 RUN apt update && apt install wget -y && rm -rf /var/lib/apt/lists/*
 
-# 1. THE MAIN MODEL: Using Q4_K_M for speed on 2vCPUs
-RUN wget "https://huggingface.co/unsloth/gemma-3n-E2B-it-GGUF/resolve/main/gemma-3n-E2B-it-Q4_K_M.gguf" -O /model.gguf
 
-# Run the server natively (Text-Only Mode)
-# -c 4096 is the safety limit to prevent RAM crashes
+# 1. THE MAIN MODEL: LFM2.5-2.6B in Q4_K_M for balanced speed and performance on CPU
+RUN wget "https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF/resolve/main/LFM2.5-2.6B-Q4_K_M.gguf" -O /model.gguf
+
+
+# Clear the entrypoint and use shell form CMD to silence all logs
 ENTRYPOINT []
-CMD /app/llama-server -m /model.gguf -t 2 --port 7860 --host 0.0.0.0 -c 4096 --temp 1.0 --log-disable > /dev/null 2>&1
+CMD /app/llama-server -m /model.gguf --port 7860 --host 0.0.0.0 -t 2 --mlock --no-mmap -c 8192 --batch-size 512 --ubatch-size 512 --log-disable > /dev/null 2>&1