From 29e642a4826e57e15eea8b836927eaed76962da6 Mon Sep 17 00:00:00 2001
From: Awni Hannun <awni@apple.com>
Date: Mon, 18 Dec 2023 10:58:43 -0800
Subject: [PATCH] readme updates

---
 t5/README.md | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/t5/README.md b/t5/README.md
index 5b173d42..89654a37 100644
--- a/t5/README.md
+++ b/t5/README.md
@@ -1,20 +1,33 @@
 # T5
 
-[T5](https://arxiv.org/pdf/1910.10683.pdf) are encoder-decoder models pre-trained on a multi-task mixture of unsupervised and supervised tasks. T5 works well on a variety of tasks out-of-the-box by prepending a different prefix to the input corresponding to each task, e.g.: `translate English to German: …`, `summarize: ….`
+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:
 
 ```sh
-python convert.py --model t5-small
+python convert.py --model <model>
 ```
 
-This will make the `{model}.npz` file which MLX can read.
+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  |
 
 ## Generate
 
-To run the model, use the `t5.py` script:
+To gneerate text with the model, use the `t5.py` script:
 
 ```sh
 python t5.py --model t5-small --prompt "translate English to German: A tasty apple"
@@ -27,3 +40,6 @@ To see a list of options run:
 ```sh
 python t5.py --help
 ```
+
+[^1]: For more information on T5 see the [original paper](https://arxiv.org/abs/1910.10683)
+   or the [Hugging Face page](https://huggingface.co/docs/transformers/model_doc/t5).