Spaces:
Paused
Paused
File size: 1,270 Bytes
4800ee4 2843355 4800ee4 08e9897 20333be 2843355 904b6ba 4800ee4 37253ef ad491af 4800ee4 8e6d05f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 |
FROM python:3.9
WORKDIR /code
# Install wget
RUN apt-get update && apt-get install -y wget
# Copy the requirements.txt file into the container at /code/requirements.txt
COPY ./requirements.txt /code/requirements.txt
# Install the Python packages specified in requirements.txt
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
# Set the environment variable for the transformers cache
ENV TRANSFORMERS_CACHE=/code/cache/huggingface/transformers
ENV HF_HOME=/code/cache/huggingface
# Create the cache directory with correct permissions
RUN mkdir -p /code/cache/huggingface/transformers && \
chmod -R 777 /code/cache/huggingface
# Download the llama-2-7b-chat.ggmlv3.q8_0.bin model file into the container
# Replace the URL below with the actual URL from where the model file should be downloaded
RUN wget -O /code/llama-2-7b-chat.ggmlv3.q8_0.bin https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q8_0.bin
# Copy the main.py script into the container
COPY ./main.py /code/main.py
COPY ./model_on_cli.py /code/model_on_cli.py
COPY ./db_faiss /code/db_faiss
# Set the command to run the Uvicorn server, serving the app defined in main.py
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|