Update Dockerfile

Dockerfile

@@ -2,11 +2,11 @@ FROM ghcr.io/ggml-org/llama.cpp:server
 
 RUN apt update && apt install wget -y && rm -rf /var/lib/apt/lists/*
 
-# THE MAIN MODEL: Gemma 2 2B Instruct (Q4_K_M)
-# This model uses knowledge distillation for superior reasoning and Hindi fluency.
-RUN wget "https://huggingface.co/bartowski/gemma-2-2b-it-GGUF/resolve/main/gemma-2-2b-it-Q4_K_M.gguf" -O /model.gguf
+# 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
 CMD ["-m", "/model.gguf", \
      "--port", "7860", "--host", "0.0.0.0", \
-     "-t", "2", "--mlock", "-c", "8192"]
+     "-t", "2", "--mlock", "-c", "8196"]