Update modeling_chatglm.py

modeling_chatglm.py

@@ -1417,7 +1417,7 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
                 break
             yield input_ids
 
-    def quantize(self, bits: int, empty_init=False, **kwargs):
+    def quantize(self, bits: int, empty_init=False, **kwargs):  # 量化
         if bits == 0:
             return
 
@@ -1431,5 +1431,5 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
 
         self.config.quantization_bit = bits
 
-        self.transformer = quantize(self.transformer, bits, empty_init=empty_init, **kwargs)
+        self.transformer = quantize(self.transformer, bits, empty_init=empty_init, **kwargs) 
         return self