Update README.md

README.md

@@ -13,15 +13,20 @@ tags:
 license: apache-2.0
 ---
 
-# ONNX convert of t5-small
-
-## Conversion of [t5-small](https://huggingface.co/t5-small)
+## [t5-small](https://huggingface.co/t5-small) exported to the ONNX format
 
 ## Model description
 
-More information needed
+[T5](https://huggingface.co/docs/transformers/model_doc/t5#t5) is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.
+
+For more information, please take a look at the original paper.
+
+Paper: [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/pdf/1910.10683.pdf)
+
+Authors: *Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu*
+
 
-## Intended uses & limitations
+## Usage example
 
 You can use this model with Transformers *pipeline*.
 
@@ -30,8 +35,7 @@ from transformers import AutoTokenizer, pipeline
 from optimum.onnxruntime import ORTModelForSeq2SeqLM
 tokenizer = AutoTokenizer.from_pretrained("optimum/t5-small")
 model = ORTModelForSeq2SeqLM.from_pretrained("optimum/t5-small")
-translator = pipeline("translation_en_to_de", model=model, tokenizer=tokenizer)
-example = "My name is Wolfgang and I live in Berlin"
-results = translator(example)
+translator = pipeline("translation_en_to_fr", model=model, tokenizer=tokenizer)
+results = translator("My name is Eustache and I have a pet raccoon")
 print(results)
 ```