Fix https://github.com/huggingface/peft/issues/1974#issue-2437471248

modeling_chatglm.py

@@ -872,7 +872,10 @@ class ChatGLMModel(ChatGLMPreTrainedModel):
         use_cache = use_cache if use_cache is not None else self.config.use_cache
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
-        batch_size, seq_length = input_ids.shape
+        if input_ids is not None:
+            batch_size, seq_length = input_ids.shape
+        else:
+            batch_size, seq_length, _ = inputs_embeds.shape
 
         if inputs_embeds is None:
             inputs_embeds = self.embedding(input_ids)