Update README.md

README.md

@@ -56,7 +56,7 @@ inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 del inputs['token_type_ids']
 streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
-output_text = tokenizer.decode(output[0], skip_prompt=True, skip_special_tokens=True)
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
 ```
 
 **Our model can handle >10k input tokens thanks to the `rope_scaling` option.**