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

While we have not yet released GPT-2 itself, you can see some unconditional samples from it:

• gpt2-samples.txt (with default settings of temperature 1 and no truncation)
• gpt2-topk40-samples.txt (with temperature 1 and top_k=40 truncation)

To give the model custom prompts, you can use:

python3 src/interactive_conditional_samples.py --top_k 40

Install python package flask and run locally with:

FLASK_APP=src/flask_conditional_samples.py flask run -p 8000

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

We are still considering release of the larger models.

Coming soon!