Update tokenization_chatglm.py

support set self.padding_side 'right'.

tokenization_chatglm.py

@@ -380,8 +380,7 @@ class ChatGLMTokenizer(PreTrainedTokenizer):
         # Load from model defaults
         bos_token_id = self.sp_tokenizer[self.bos_token]
         mask_token_id = self.sp_tokenizer[self.mask_token]
-        gmask_token_id = self.sp_tokenizer[self.gmask_token]
-        assert self.padding_side == "left"
+        gmask_token_id = self.sp_tokenizer[self.gmask_token]        
 
         required_input = encoded_inputs[self.model_input_names[0]]
         seq_length = len(required_input)
@@ -424,20 +423,35 @@ class ChatGLMTokenizer(PreTrainedTokenizer):
 
         if needs_to_be_padded:
             difference = max_length - len(required_input)
-
-            if "attention_mask" in encoded_inputs:
-                encoded_inputs["attention_mask"] = np.pad(encoded_inputs["attention_mask"],
-                                                          pad_width=[(0, 0), (difference, 0), (difference, 0)],
-                                                          mode='constant', constant_values=True)
-            if "token_type_ids" in encoded_inputs:
-                encoded_inputs["token_type_ids"] = [self.pad_token_type_id] * difference + encoded_inputs[
-                    "token_type_ids"
-                ]
-            if "special_tokens_mask" in encoded_inputs:
-                encoded_inputs["special_tokens_mask"] = [1] * difference + encoded_inputs["special_tokens_mask"]
-            if "position_ids" in encoded_inputs:
-                encoded_inputs["position_ids"] = np.pad(encoded_inputs["position_ids"],
-                                                        pad_width=[(0, 0), (difference, 0)])
-            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
+            if self.padding_side == "left":
+                if "attention_mask" in encoded_inputs:
+                    encoded_inputs["attention_mask"] = np.pad(encoded_inputs["attention_mask"],
+                                                            pad_width=[(0, 0), (difference, 0), (difference, 0)],
+                                                            mode='constant', constant_values=True)
+                if "token_type_ids" in encoded_inputs:
+                    encoded_inputs["token_type_ids"] = [self.pad_token_type_id] * difference + encoded_inputs[
+                        "token_type_ids"
+                    ]
+                if "special_tokens_mask" in encoded_inputs:
+                    encoded_inputs["special_tokens_mask"] = [1] * difference + encoded_inputs["special_tokens_mask"]
+                if "position_ids" in encoded_inputs:
+                    encoded_inputs["position_ids"] = np.pad(encoded_inputs["position_ids"],
+                                                            pad_width=[(0, 0), (difference, 0)])
+                encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
+            elif self.padding_side == "right":
+                if "attention_mask" in encoded_inputs:
+                    encoded_inputs["attention_mask"] = np.pad(encoded_inputs["attention_mask"],
+                                                            pad_width=[(0, 0), (0, difference), (0, difference)],
+                                                            mode='constant', constant_values=True)
+                if "token_type_ids" in encoded_inputs:
+                    encoded_inputs["token_type_ids"] = encoded_inputs[ "token_type_ids" ] + [self.pad_token_type_id] * difference
+                if "special_tokens_mask" in encoded_inputs:
+                    encoded_inputs["special_tokens_mask"] = encoded_inputs["special_tokens_mask"] + [1] * difference
+                if "position_ids" in encoded_inputs:
+                    encoded_inputs["position_ids"] = np.pad(encoded_inputs["position_ids"],
+                                                            pad_width=[(0, 0), (0, difference)])
+                encoded_inputs[self.model_input_names[0]] = required_input + [self.pad_token_id] * difference
+            else:
+                raise ValueError("Invalid padding strategy:" + str(self.padding_side))
 
         return encoded_inputs