Add a Dockerfile and document usage in README

Dockerfile.cpu

+FROM tensorflow/tensorflow:1.12.0-py3
+
+ENV LANG=C.UTF-8
+RUN mkdir /gpt-2 
+WORKDIR /gpt-2
+COPY requirements.txt download_model.sh /gpt-2/
+RUN apt-get update && \
+    apt-get install -y curl && \
+    sh download_model.sh 117M
+RUN pip3 install -r requirements.txt
+
+ADD . /gpt-2

Dockerfile.gpu

+FROM tensorflow/tensorflow:1.12.0-gpu-py3
+
+# nvidia-docker 1.0
+LABEL com.nvidia.volumes.needed="nvidia_driver"
+LABEL com.nvidia.cuda.version="${CUDA_VERSION}"
+
+# nvidia-container-runtime
+ENV NVIDIA_VISIBLE_DEVICES=all \
+    NVIDIA_DRIVER_CAPABILITIES=compute,utility \
+    NVIDIA_REQUIRE_CUDA="cuda>=8.0" \
+    LANG=C.UTF-8
+
+RUN mkdir /gpt-2
+WORKDIR /gpt-2
+COPY requirements.txt download_model.sh /gpt-2/
+RUN apt-get update && \
+    apt-get install -y curl && \
+    sh download_model.sh 117M
+RUN pip3 install -r requirements.txt
+
+ADD . /gpt-2

README.md

@@ -13,6 +13,8 @@ Git clone this repository, and `cd` into directory for remaining commands
 git clone https://github.com/openai/gpt-2.git && cd gpt-2
 ```
 
+### Native Installation
+
 Download the model data
 ```
 sh download_model.sh 117M
@@ -34,6 +36,21 @@ Install other python packages:
 pip3 install -r requirements.txt
 ```
 
+### Docker Installation
+
+Build the Dockerfile and tag the created image as `gpt-2`:
+```
+docker build --tag gpt-2 -f Dockerfile.gpu . # or Dockerfile.cpu
+```
+
+Start an interactive bash session from the `gpt-2` docker image.
+
+You can opt to use the `--runtime=nvidia` flag if you have access to a NVIDIA GPU
+and a valid install of [nvidia-docker 2.0](https://github.com/nvidia/nvidia-docker/wiki/Installation-(version-2.0)).
+```
+docker run --runtime=nvidia -it gpt-2 bash
+```
+
 ## Usage
 
 | WARNING: Samples are unfiltered and may contain offensive content. |