Update Dockerfile

Dockerfile

@@ -2,24 +2,54 @@ FROM ghcr.io/ggml-org/llama.cpp:full
 
 WORKDIR /app
 
-RUN apt update && apt install -y python3 python3-pip python3-venv
+# Install Python
+RUN apt-get update && \
+    apt-get install -y python3 python3-pip python3-venv && \
+    rm -rf /var/lib/apt/lists/*
+
 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", "128000", \
-     "-n", "38912"]
+# Install HuggingFace Hub
+RUN pip install --no-cache-dir -U pip huggingface_hub
+
+# Download Model
+RUN python3 -c "from huggingface_hub import hf_hub_download; \
+hf_hub_download( \
+repo_id='Qwen/Qwen2.5-Coder-3B-Instruct-GGUF', \
+filename='qwen2.5-coder-3b-instruct-q4_k_m.gguf', \
+local_dir='/app')"
+
+CMD [
+"--server",
+
+"-m",
+"/app/qwen2.5-coder-3b-instruct-q4_k_m.gguf",
+
+"--host",
+"0.0.0.0",
+
+"--port",
+"7860",
+
+"-t",
+"4",
+
+"-b",
+"1024",
+
+"-c",
+"16384",
+
+"-n",
+"4096",
+
+"--parallel",
+"1",
+
+"--cache-type-k",
+"q8_0",
+
+"--cache-type-v",
+"q8_0"
+]