Change usage section

README.md

@@ -23,25 +23,29 @@ This enables to specify:
 ## Usage
 
 The model is instantiated the same way as in the Transformers library.
-The only difference is that there are a few new training arguments specific to HPUs:
-
-```
-from optimum.habana import GaudiTrainer, GaudiTrainingArguments
-from transformers import T5Tokenizer, T5Model
-
-tokenizer = T5Tokenizer.from_pretrained('t5-base')
-model = T5Model.from_pretrained('t5-base')
-args = GaudiTrainingArguments(
-    output_dir="/tmp/output_dir",
-    use_habana=True,
-    use_lazy_mode=True,
-    gaudi_config_name="Habana/t5",
-)
-
-trainer = GaudiTrainer(
-    model=model,
-    args=args,
-    tokenizer=tokenizer,
-)
-trainer.train()
+The only difference is that there are a few new training arguments specific to HPUs.
+
+[Here](https://github.com/huggingface/optimum-habana/blob/main/examples/question-answering/run_summarization.py) is a summarization example script to fine-tune a model. You can run it with T5-small with the following command:
+```bash
+python run_summarization.py \
+    --model_name_or_path t5-small \
+    --do_train \
+    --do_eval \
+    --dataset_name cnn_dailymail \
+    --dataset_config "3.0.0" \
+    --source_prefix "summarize: " \
+    --output_dir /tmp/tst-summarization \
+    --per_device_train_batch_size 4 \
+    --per_device_eval_batch_size 4 \
+    --overwrite_output_dir \
+    --predict_with_generate \
+    --use_habana \
+    --use_lazy_mode \
+    --gaudi_config_name Habana/t5 \
+    --ignore_pad_token_for_loss False \
+    --pad_to_max_length \
+    --save_strategy epoch \
+    --throughput_warmup_steps 2
 ```
+
+Check the [documentation](https://huggingface.co/docs/optimum/habana/index) out for more advanced usage and examples.