Spaces:

Unmid
/

hf_dead

Paused

hf_dead / Dockerfile

Nafiul Huda

Update Dockerfile

7cfb924 verified 7 months ago

1.29 kB

# Stage 1: Build llama.cpp
FROM ubuntu:22.04 AS builder

RUN apt-get update && apt-get install -y \
    build-essential \
    cmake \
    git \
    libcurl4-openssl-dev \
    python3-pip

# Clone raw llama.cpp
WORKDIR /app
RUN git clone https://github.com/ggml-org/llama.cpp.git .

# Build with UI DISABLED for a pure headless API
# We also enable cURL support for remote model loading if needed
RUN cmake -B build \
    -DLLAMA_BUILD_WEBUI=OFF \
    -DLLAMA_CURL=ON \
    -DLLAMA_BUILD_EXAMPLES=OFF
RUN cmake --build build --config Release -j $(nproc) --target llama-server

# Stage 2: Runtime
FROM ubuntu:22.04

RUN apt-get update && apt-get install -y libcurl4 python3-pip && rm -rf /var/lib/apt/lists/*
RUN pip install huggingface_hub

WORKDIR /app
COPY --from=builder /app/build/bin/llama-server /app/llama-server

# Download official Qwen GGUF (Non-Unsloth)
RUN python3 -c 'from huggingface_hub import hf_hub_download; \
    hf_hub_download(repo_id="Qwen/Qwen2.5-7B-Instruct-GGUF", \
    filename="qwen2.5-7b-instruct-q4_k_m.gguf", local_dir="/app")'

# HF Spaces run on 7860
EXPOSE 7860

# Run headless server
CMD ["./llama-server", \
     "-m", "/app/qwen2.5-7b-instruct-q4_k_m.gguf", \
     "--host", "0.0.0.0", \
     "--port", "7860", \
     "-c", "32768", \
     "--embedding"]

	# Stage 1: Build llama.cpp
	FROM ubuntu:22.04 AS builder

	RUN apt-get update && apt-get install -y \
	build-essential \
	cmake \
	git \
	libcurl4-openssl-dev \
	python3-pip

	# Clone raw llama.cpp
	WORKDIR /app
	RUN git clone https://github.com/ggml-org/llama.cpp.git .

	# Build with UI DISABLED for a pure headless API
	# We also enable cURL support for remote model loading if needed
	RUN cmake -B build \
	-DLLAMA_BUILD_WEBUI=OFF \
	-DLLAMA_CURL=ON \
	-DLLAMA_BUILD_EXAMPLES=OFF
	RUN cmake --build build --config Release -j $(nproc) --target llama-server

	# Stage 2: Runtime
	FROM ubuntu:22.04

	RUN apt-get update && apt-get install -y libcurl4 python3-pip && rm -rf /var/lib/apt/lists/*
	RUN pip install huggingface_hub

	WORKDIR /app
	COPY --from=builder /app/build/bin/llama-server /app/llama-server

	# Download official Qwen GGUF (Non-Unsloth)
	RUN python3 -c 'from huggingface_hub import hf_hub_download; \
	hf_hub_download(repo_id="Qwen/Qwen2.5-7B-Instruct-GGUF", \
	filename="qwen2.5-7b-instruct-q4_k_m.gguf", local_dir="/app")'

	# HF Spaces run on 7860
	EXPOSE 7860

	# Run headless server
	CMD ["./llama-server", \
	"-m", "/app/qwen2.5-7b-instruct-q4_k_m.gguf", \
	"--host", "0.0.0.0", \
	"--port", "7860", \
	"-c", "32768", \
	"--embedding"]