Update README.md

README.md

@@ -10,25 +10,25 @@ pipeline_tag: text2text-generation
 from transformers import pipeline
 
 # Load the model from the Hugging Face Model Hub
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
-tokenizer = AutoTokenizer.from_pretrained("ihgn/similar-questions")
-model = AutoModelForSeq2SeqLM.from_pretrained("ihgn/similar-questions")
-model = pipeline("text2text-generation", model=model_name)
+    from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+    tokenizer = AutoTokenizer.from_pretrained("ihgn/similar-questions")
+    model = AutoModelForSeq2SeqLM.from_pretrained("ihgn/similar-questions")
+    model = pipeline("text2text-generation", model=model_name)
 
 # Configure the generation parameters
-generation_config = {
-    "max_length": 512,
-    "num_beams": 1,
-    "top_k": 50,
-    "top_p": 0.92,
-    "do_sample": True,
-    "num_return_sequences": 1
-}
+    generation_config = {
+        "max_length": 512,
+        "num_beams": 1,
+        "top_k": 50,
+        "top_p": 0.92,
+        "do_sample": True,
+        "num_return_sequences": 1
+    }
 
 # Generate text using the configured parameters
-input_text= "Your input text goes here."
-input_ids = tokenizer.encode(input_text, return_tensors="pt")
-generated_ids = model(input_ids, **generation_config)
-generated_text = tokenizer.decode(generated_ids.squeeze(), skip_special_tokens=True)
+    input_text= "Your input text goes here."
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+    generated_ids = model(input_ids, **generation_config)
+    generated_text = tokenizer.decode(generated_ids.squeeze(), skip_special_tokens=True)
 # Print the generated text
-print(generated_text)
+    print(generated_text)