This is an implementation of T5-Base as a Cog model. Cog packages machine learning models as standard containers.
First, install cog in codespace:
curl https://replicate.github.io/codespaces/scripts/install-cog.sh | bash
Next, download the pre-trained weights:
cog run script/download-weights.py
Then you can generate text based on input prompts:
cog predict -i prompt="Q: Answer the following yes/no question by reasoning step-by-step. Can a dog drive a car?"