Code and samples from the paper "Language Models are Unsupervised Multitask Learners".

For now, we have only released a smaller (117M parameter) version of GPT-2.

See more details in our blog post.

Download the model data

sh download_model.sh 117M

Install python packages:

pip3 install -r requirements.txt

To generate unconditional samples from the small model:

python3 src/generate_unconditional_samples.py | tee samples

There are various flags for controlling the samples:

python3 src/generate_unconditional_samples.py --top_k 40 --temperature 0.7 | tee samples

To give the model custom prompts, you can use:

python3 src/interactive_conditional_samples.py --top_k 40

While we have not yet released GPT-2 itself, you can see some samples from it in the gpt-2-samples folder. We show unconditional samples with default settings (temperature 1 and no truncation), with temperature 0.7, and with truncation with top_k 40.

We may release code for evaluating the models on various benchmarks.

We are still considering release of the larger models.

Coming soon!