Update fine_tuning.py

fine_tuning.py

@@ -16,7 +16,6 @@ def clean_text(text):
     text = re.sub(r'\d+', '', text)
     text = text.lower()
     text = " ".join([word for word in text.split() if word not in stop_words])
-    text = " ".join([ps.stem(word) for word in word_tokenize(text)])
     return text
 
 # Prompts okuma
@@ -40,7 +39,7 @@ def prepare_data(input_texts, target_texts):
 
 # Paraphrasing fonksiyonu
 def paraphrase_with_model(text, model, tokenizer):
-    prompt = "paraphrase: " + text
+    prompt = "Teach the following content: " + text
     inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=512)
     output_ids = model.generate(
         inputs["input_ids"],