Update README.md

README.md

@@ -13,4 +13,16 @@ tags:
 pipeline_tag: text2text-generation
 ---
 # CGEDit - Chinese Grammatical Error Diagnosis by Task-Specific Instruction Tuning
-![CGEDit_model.png](https://cdn-uploads.huggingface.co/production/uploads/64c7473f513a7fa7c32e153b/AtlsZUWz86rKyb_9EWlDa.png)
+![CGEDit_model.png](https://cdn-uploads.huggingface.co/production/uploads/64c7473f513a7fa7c32e153b/AtlsZUWz86rKyb_9EWlDa.png)
+
+## Usage
+```python
+from transformers import AutoTokenizer, T5ForConditionalGeneration
+
+tokenizer = AutoTokenizer.from_pretrained("CodeTed/CGEDit")
+model = T5ForConditionalGeneration.from_pretrained("CodeTed/CGEDit")
+input_text = '糾正句子裡的錯字: 看完那段文張，我是反對的！'
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids
+outputs = model.generate(input_ids, max_length=256)
+edited_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```