# FROM ghcr.io/ggml-org/llama.cpp:server

# RUN apt update && apt install wget -y && rm -rf /var/lib/apt/lists/*

# RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/gemma-4-E2B-it-qat-UD-Q4_K_XL.gguf" -O /gemma-4-E2B-it-qat-UD-Q4_K_XL.gguf

# RUN wget "https://huggingface.co/Dorjzodovsuren/Mongolian_Llama3-v0.1/resolve/main/Mongolian_Llama3-v1.Q4_K_M.gguf" -O /mongolian_llama.gguf

# RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/mtp-gemma-4-E2B-it.gguf" -O /mtp-gemma-4-E2B-it.gguf

# RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/mmproj-F16.gguf" -O /gemma-4-E2B-it-mmproj.gguf

# CMD [ \
#   "-m", "/mongolian_llama.gguf", \
#   "--spec-draft-model", "/mtp-gemma-4-E2B-it.gguf", \
#   "--mmproj", "/gemma-4-E2B-it-mmproj.gguf", \
#   "--port", "7860", \
#   "--host", "0.0.0.0", \
#   "-t", "2", \
#   "-tb", "2", \
#   "-fa", "on", \
#   "-ub", "128", \
#   "-b", "512", \
#   "--spec-type", "draft-mtp", \
#   "--spec-draft-n-max", "3" \
# ]

FROM ghcr.io/ggml-org/llama.cpp:server

RUN apt update && apt install wget -y && rm -rf /var/lib/apt/lists/*

RUN wget "https://huggingface.co/Dorjzodovsuren/Mongolian_Llama3-v0.1/resolve/main/Mongolian_Llama3-v1.Q4_K_M.gguf" -O /mongolian_llama.gguf

CMD [ \
  "-m", "/mongolian_llama.gguf", \
  "--port", "7860", \
  "--host", "0.0.0.0", \
  "-t", "2", \
  "-tb", "2", \
  "-fa", "on", \
  "-ub", "128", \
  "-b", "512" \
]