rounding

app.py

@@ -79,7 +79,7 @@ def create_response(input_str,
       len_exp_tensor_list = torch.numel(scores)
       average_exp_tensor_list = sum_exp_tensor_list / len_exp_tensor_list
       print(average_exp_tensor_list)
-      score_list.append(average_exp_tensor_list.item())
+      score_list.append(round(average_exp_tensor_list.item(),2))
   outputs = model_name+" generated <br>"
   for index, output_id in enumerate(output.sequences):
       sentence = tokenizer.decode(output_id, skip_special_tokens=True)
@@ -91,7 +91,7 @@ def create_response(input_str,
   return outputs
 
 
-common_examples_string="<br/>Sample Inputs:<br/>What is death?<br/>One of the best teachers in all of life turns out to be what?<br/>what is your most meaningful relationship?\nWhat actually gives life meaning?<br/>"
+common_examples_string="<br/>Sample Inputs:<br/>What is death?<br/>One of the best teachers in all of life turns out to be what?<br/>what is your most meaningful relationship?<br/>What actually gives life meaning?<br/>"
 common_examples=[ 
       ["What is death?",default_num_return_sequences,default_temperature,default_repetition_penalty,default_top_p,default_top_k,default_do_sample], # The first example
       ["One of the best teachers in all of life turns out to be what?",default_num_return_sequences,default_temperature,default_repetition_penalty,default_top_p,default_top_k,default_do_sample], # The second example