Update README.md

README.md

@@ -35,7 +35,7 @@ def summarize(text, tokenizer, model, num_beams=4, temperature=1, max_new_tokens
     in_data = inputs.input_ids.to('cuda')
     attention_mask = inputs.attention_mask.to('cuda')
     output_ids = model.generate(input_ids=in_data, attention_mask=attention_mask, num_beams=num_beams, max_new_tokens=max_new_tokens, do_sample=True, early_stopping=True, use_cache=True, temperature=temperature, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id)
-    generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=False)
+    generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
     
     return generated_text
 
@@ -66,7 +66,7 @@ def summarize_batch(texts, tokenizer, model, num_beams=4, temperature=1, max_new
         eos_token_id=tokenizer.eos_token_id
     )
 
-    generated_texts = [tokenizer.decode(output, skip_special_tokens=False) for output in output_ids]
+    generated_texts = [tokenizer.decode(output, skip_special_tokens=True) for output in output_ids]
     
     return generated_texts