Update README.md

README.md

@@ -62,4 +62,22 @@ The following hyperparameters were used during training:
 - Transformers 4.35.0
 - Pytorch 2.1.0
 - Datasets 2.14.6
-- Tokenizers 0.14.1
+- Tokenizers 0.14.1
+
+## Inference API
+이 섹션에서는 `bert-base-uncased` 모델을 사용하여 텍스트 분류 작업을 수행하는 방법을 보여주는 예제 코드를 변경할 수 있습니다.
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+model_name = "CDRI-Eddy/ingredients_classification_model"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+nlp = pipeline("text-classification", model=model, tokenizer=tokenizer)
+
+# 예제 입력 문장 변경
+input_sentence = "Here is the sentence you want the model to classify."
+result = nlp(input_sentence)
+
+print(result)