Update README.md

README.md

@@ -20,6 +20,27 @@ You can use the raw model for text generation or fine-tune it to a downstream ta
 
 Note that the texts should be segmented into words using Juman++ in advance.
 
+### How to use
+
+You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:
+
+```python
+from transformers import pipeline, set_seed
+generator = pipeline('text-generation', model='nlp-waseda/gpt2-xl-japanese')
+
+set_seed(42)
+generator("早稲田 大学 で 自然 言語 処理 を", max_length=30, do_sample=True, pad_token_id=2, num_return_sequences=5)
+```
+
+```python
+from transformers import ReformerTokenizer, GPT2Model
+tokenizer = ReformerTokenizer.from_pretrained('nlp-waseda/gpt2-small-japanese')
+model = GPT2Model.from_pretrained('nlp-waseda/gpt2-small-japanese')
+text = "早稲田 大学 で 自然 言語 処理 を"
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+```
+
 ### Preprocessing
 
 The texts are normalized using zenhan, segmented into words using Juman++, and tokenized using SentencePiece. Juman++ 2.0.0-rc3 was used for pretraining.