Dockerfile

FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y libgomp1 wget && rm -rf /var/lib/apt/lists/*

# Use a single-line RUN to prevent URL truncation and Job Timeout
RUN pip install --no-cache-dir huggingface_hub llama-cpp-python[server] --extra-index-url https://abetlen.github.io

# Model settings
ENV REPO_ID="tensorblock/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF"
ENV FILENAME="WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-Q2_K.gguf"

# RUNTIME: Download and Start (happens in Logs tab, not Build tab)
CMD python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='$REPO_ID', filename='$FILENAME', local_dir='.')" && \
    python3 -m llama_cpp.server --model ./$FILENAME --host 0.0.0.0 --port 7860 --n_ctx 1024 --n_threads 2