Add lookup generate in load_low_bit (#12243)

* add lookup generate in load_low_bit

* update comment

python/llm/src/ipex_llm/transformers/model.py

@@ -797,6 +797,13 @@ class _BaseAutoModelClass:
                                                                 model)
             torch.distributed.barrier()
 
+        # add lookup_generate to loaded model
+        from .lookup import lookup_generate
+        import types
+        model.lookup_generate = types.MethodType(lookup_generate, model)
+        if model.config.model_type == "minicpmv" and hasattr(model, 'llm'):
+            model.llm.lookup_generate = types.MethodType(lookup_generate, model.llm)
+
         return model