mlx-examples/t5/README.md

T5

The T5 models are encoder-decoder models pre-trained on a mixture of unsupervised and supervised tasks.¹ These models work well on a variety of tasks by prepending task-specific prefixes to the input, e.g.: translate English to German: …, summarize: …., etc.

Setup

Download and convert the model:

python convert.py --model <model>

This will make the <model>.npz file which MLX can read.

The <model> can be any of the following:

Model Name	Model Size
t5-small	60 million
t5-base	220 million
t5-large	770 million
t5-3b	3 billion
t5-11b	11 billion

It also supports t5 variants, such as google/flan-t5-small, google/flan-t5-base, etc.

Generate

Generate text with:

python t5.py --model t5-small --prompt "translate English to German: A tasty apple"

This should give the output: Ein leckerer Apfel

To see a list of options run:

python t5.py --help

---

1. For more information on T5 see the original paper or the Hugging Face page. ↩︎