let's switch back to CPU, it's the only thing that works

Dockerfile

@@ -1,81 +1,29 @@
-FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
-LABEL maintainer="Hugging Face"
+FROM node:18
 
-ENV PYTHONUNBUFFERED 1
+# Set up a new user named "user" with user ID 1000
+RUN useradd -o -u 1000 user
 
-EXPOSE 7860
-
-ARG DEBIAN_FRONTEND=noninteractive
-
-# Use login shell to read variables from `~/.profile` (to pass dynamic created variables between RUN commands)
-SHELL ["sh", "-lc"]
-
-RUN apt update
-
-RUN apt --yes install build-essential
-
-RUN apt --yes install curl
-
-RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash -
-
-RUN apt --yes install nodejs
-
-# we need Rust
-RUN curl https://sh.rustup.rs -sSf | sh -s -- --default-toolchain nightly -y
-
-# configure PNPM
-
-RUN corepack enable
-RUN corepack prepare [email protected] --activate
-
-RUN apt --yes install git git-lfs libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
-
-RUN git lfs install
-
-RUN python3 -m pip install --no-cache-dir --upgrade pip
-
-WORKDIR /tmp
-
-# ok! let's try to compile llama-node
-RUN git clone https://github.com/Atome-FE/llama-node.git
-
-WORKDIR /tmp/llama-node
-
-RUN git submodule update --init --recursive
-
-RUN pnpm install --ignore-scripts
-
-# let's try to build backends, to see
-RUN pnpm build:llama-cpp
-
-RUN pnpm:build
-
-WORKDIR /tmp/llama-node/packages/llama-cpp
-
-RUN pnpm build:cuda
-
-ENV LD_LIBRARY_PATH $LD_LIBRARY_PATH:$HOME/.llama-node
-
-RUN useradd -m -u 1000 user
+# Switch to the "user" user
 USER user
+
+# Set home to the user's home directory
 ENV HOME=/home/user \
 	PATH=/home/user/.local/bin:$PATH
 
+# Set the working directory to the user's home directory
 WORKDIR $HOME/app
 
-# prepare to install the Node app
-COPY --chown=user package*.json .
-
-RUN pnpm --version
+# Install app dependencies
+# A wildcard is used to ensure both package.json AND package-lock.json are copied
+# where available (npm@5+)
+COPY --chown=user package*.json $HOME/app
 
 RUN npm install
 
-# ok.. should be good?
-
-COPY --chown=user . .
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
 
 ADD --chown=user https://huggingface.co/TheBloke/airoboros-13b-gpt4-GGML/resolve/main/airoboros-13b-gpt4.ggmlv3.q4_0.bin models/airoboros-13b-gpt4.ggmlv3.q4_0.bin
 
-RUN python3 test.py
-
-CMD [ "pnpm", "run", "start" ]
+EXPOSE 7860
+CMD [ "npm", "run", "start" ]

Dockerfile.cpu

@@ -0,0 +1,29 @@
+FROM node:18
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -o -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Install app dependencies
+# A wildcard is used to ensure both package.json AND package-lock.json are copied
+# where available (npm@5+)
+COPY --chown=user package*.json $HOME/app
+
+RUN npm install
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+ADD --chown=user https://huggingface.co/TheBloke/airoboros-13b-gpt4-GGML/resolve/main/airoboros-13b-gpt4.ggmlv3.q4_0.bin models/airoboros-13b-gpt4.ggmlv3.q4_0.bin
+
+EXPOSE 7860
+CMD [ "npm", "run", "start" ]

Dockerfile.gpu

@@ -0,0 +1,81 @@
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
+LABEL maintainer="Hugging Face"
+
+ENV PYTHONUNBUFFERED 1
+
+EXPOSE 7860
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Use login shell to read variables from `~/.profile` (to pass dynamic created variables between RUN commands)
+SHELL ["sh", "-lc"]
+
+RUN apt update
+
+RUN apt --yes install build-essential
+
+RUN apt --yes install curl
+
+RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash -
+
+RUN apt --yes install nodejs
+
+# we need Rust
+RUN curl https://sh.rustup.rs -sSf | sh -s -- --default-toolchain nightly -y
+
+# configure PNPM
+
+RUN corepack enable
+RUN corepack prepare [email protected] --activate
+
+RUN apt --yes install git git-lfs libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
+
+RUN git lfs install
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+
+WORKDIR /tmp
+
+# ok! let's try to compile llama-node
+RUN git clone https://github.com/Atome-FE/llama-node.git
+
+WORKDIR /tmp/llama-node
+
+RUN git submodule update --init --recursive
+
+RUN pnpm install --ignore-scripts
+
+# let's try to build backends, to see
+RUN pnpm build:llama-cpp
+
+RUN pnpm:build
+
+WORKDIR /tmp/llama-node/packages/llama-cpp
+
+RUN pnpm build:cuda
+
+ENV LD_LIBRARY_PATH $LD_LIBRARY_PATH:$HOME/.llama-node
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+# prepare to install the Node app
+COPY --chown=user package*.json .
+
+RUN pnpm --version
+
+RUN npm install
+
+# ok.. should be good?
+
+COPY --chown=user . .
+
+ADD --chown=user https://huggingface.co/TheBloke/airoboros-13b-gpt4-GGML/resolve/main/airoboros-13b-gpt4.ggmlv3.q4_0.bin models/airoboros-13b-gpt4.ggmlv3.q4_0.bin
+
+RUN python3 test.py
+
+CMD [ "pnpm", "run", "start" ]