Update Dockerfile

Dockerfile

@@ -1,15 +1 @@
-# Download Logic (Qwen2.5-Coder-1.5B-Instruct)
-RUN python3 -c 'from huggingface_hub import hf_hub_download; \
-    repo="bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF"; \
-    hf_hub_download(repo_id=repo, filename="Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf", local_dir="/app")'
-
-# CMD Logic (MMProj hata diya hai kyunki coding model text-only hai)
-CMD ["--server", \
-     "-m", "/app/Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf", \
-     "--host", "0.0.0.0", \
-     "--port", "7860", \
-     "-t", "2", \
-     "--cache-type-k", "q8_0", \
-     "--cache-type-v", "iq4_nl", \
-     "-c", "32768", \
-     "-n", "32768"]
+FROM ghcr.io/ggml-org/llama.cpp:fullWORKDIR /appRUN apt update && apt install -y python3 python3-pip python3-venvRUN python3 -m venv /opt/venvENV PATH="/opt/venv/bin:$PATH"RUN pip install -U pip huggingface_hubRUN 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"]