add set_input_embedding to support resize token embedding

modeling_chatglm.py

@@ -766,6 +766,9 @@ class ChatGLMModel(ChatGLMPreTrainedModel):
     def get_input_embeddings(self):
         return self.embedding.word_embeddings
 
+    def set_input_embeddings(self, new_embeddings: torch.Tensor):
+        self.embedding.word_embeddings = new_embeddings
+
     def get_prompt(self, batch_size, device, dtype=torch.half):
         prefix_tokens = self.prefix_tokens.unsqueeze(0).expand(batch_size, -1).to(device)
         past_key_values = self.prefix_encoder(prefix_tokens).type(dtype)