Update app.py

app.py

@@ -159,13 +159,13 @@ def talk(prompt, history):
     for token in model.generate(input_ids):
     	print(model.detokenize(input_ids), end='', flush=True)
     	NUM_TOKENS+=1
-   time_generate = time.time() - start
-   print('\n')
-   print('-'*4+'End Generation'+'-'*4)
-   print(f'Num of generated tokens: {NUM_TOKENS}')
-   print(f'Time for complete generation: {time_generate}s')
-   print(f'Tokens per secound: {NUM_TOKENS/time_generate}')
-   print(f'Time per token: {(time_generate/NUM_TOKENS)*1000}ms')
+    time_generate = time.time() - start
+    print('\n')
+    print('-'*4+'End Generation'+'-'*4)
+    print(f'Num of generated tokens: {NUM_TOKENS}')
+    print(f'Time for complete generation: {time_generate}s')
+    print(f'Tokens per secound: {NUM_TOKENS/time_generate}')
+    print(f'Time per token: {(time_generate/NUM_TOKENS)*1000}ms')
 
 
     #outputtokens =  model.generate(input_ids)