Update test_quant.py

test_quant.py

@@ -14,7 +14,7 @@ def gptq():
         bits=4, # 4 or 8
         group_size=128,
         damp_percent=0.01,
-        desc_act=False,  # set to False can significantly speed up inference but the perplexity may slightly bad
+        desc_act=True,  # set to False can significantly speed up inference but the perplexity may slightly bad
         static_groups=False,
         sym=True,
         true_sequential=True,
@@ -46,7 +46,7 @@ def gptq():
                 messages.append(msg)
                 
     print('len(messages):',len(messages))
-    messages = messages[:5]
+    messages = messages[:500]
     print('len(messages):',len(messages))
     
     data = []
@@ -65,4 +65,4 @@ def gptq():
     t2 = time.time()
     print(('time:{:.2f}s').format(t2-t1))
 
-gptq()
\ No newline at end of file
+gptq()