From f58b9c05220943acf79e394e64e6d01c9ea2c04e Mon Sep 17 00:00:00 2001
From: Gorkem Ozkaya <gorkemozkaya@gmail.com>
Date: Tue, 26 Jul 2022 04:56:40 -0700
Subject: [PATCH] Update translation.mdx (#18169)

* Update translation.mdx

* update translation.mdx by running make style
---
 docs/source/en/tasks/translation.mdx | 42 +++++++++++++++++-----------
 1 file changed, 26 insertions(+), 16 deletions(-)

diff --git a/docs/source/en/tasks/translation.mdx b/docs/source/en/tasks/translation.mdx
index 0cb28736f0..4f628b06db 100644
--- a/docs/source/en/tasks/translation.mdx
+++ b/docs/source/en/tasks/translation.mdx
@@ -93,10 +93,32 @@ Use 🤗 Datasets [`~datasets.Dataset.map`] function to apply the preprocessing
 >>> tokenized_books = books.map(preprocess_function, batched=True)
 ```
 
+<frameworkcontent>
+<pt>
+Load T5 with [`AutoModelForSeq2SeqLM`]:
+
+```py
+>>> from transformers import AutoModelForSeq2SeqLM
+
+>>> model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+```
+</pt>
+<tf>
+Load T5 with [`TFAutoModelForSeq2SeqLM`]:
+
+```py
+>>> from transformers import TFAutoModelForSeq2SeqLM
+
+>>> model = TFAutoModelForSeq2SeqLM.from_pretrained("t5-small")
+```
+</tf>
+</frameworkcontent>
+
 Use [`DataCollatorForSeq2Seq`] to create a batch of examples. It will also *dynamically pad* your text and labels to the length of the longest element in its batch, so they are a uniform length. While it is possible to pad your text in the `tokenizer` function by setting `padding=True`, dynamic padding is more efficient.
 
 <frameworkcontent>
 <pt>
+
 ```py
 >>> from transformers import DataCollatorForSeq2Seq
 
@@ -104,6 +126,7 @@ Use [`DataCollatorForSeq2Seq`] to create a batch of examples. It will also *dyna
 ```
 </pt>
 <tf>
+
 ```py
 >>> from transformers import DataCollatorForSeq2Seq
 
@@ -116,13 +139,6 @@ Use [`DataCollatorForSeq2Seq`] to create a batch of examples. It will also *dyna
 
 <frameworkcontent>
 <pt>
-Load T5 with [`AutoModelForSeq2SeqLM`]:
-
-```py
->>> from transformers import AutoModelForSeq2SeqLM, Seq2SeqTrainingArguments, Seq2SeqTrainer
-
->>> model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
-```
 
 <Tip>
 
@@ -137,6 +153,8 @@ At this point, only three steps remain:
 3. Call [`~Trainer.train`] to fine-tune your model.
 
 ```py
+>>> from transformers import Seq2SeqTrainingArguments, Seq2SeqTrainer
+
 >>> training_args = Seq2SeqTrainingArguments(
 ...     output_dir="./results",
 ...     evaluation_strategy="epoch",
@@ -194,14 +212,6 @@ Set up an optimizer function, learning rate schedule, and some training hyperpar
 >>> optimizer = AdamWeightDecay(learning_rate=2e-5, weight_decay_rate=0.01)
 ```
 
-Load T5 with [`TFAutoModelForSeq2SeqLM`]:
-
-```py
->>> from transformers import TFAutoModelForSeq2SeqLM
-
->>> model = TFAutoModelForSeq2SeqLM.from_pretrained("t5-small")
-```
-
 Configure the model for training with [`compile`](https://keras.io/api/models/model_training_apis/#compile-method):
 
 ```py
@@ -222,4 +232,4 @@ For a more in-depth example of how to fine-tune a model for translation, take a
 [PyTorch notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation.ipynb)
 or [TensorFlow notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation-tf.ipynb).
 
-</Tip>
\ No newline at end of file
+</Tip>