Update README.md

README.md

@@ -80,22 +80,11 @@ def has_close_elements(numbers: List[float], threshold: float) -> bool:
 messages = [
     {"role": "user", "content": prompt}
 ]
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
-model_inputs = tokenizer([text], return_tensors="pt").to(device)
 
-generated_ids = model.generate(
-    model_inputs.input_ids,
-    max_new_tokens=512
-)
-generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+res = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
 
-response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ```
 
 ### Contact information