fix float point

intel-analytics · Jul 1, 2024 · c614dd5 · c614dd5
1 parent 5d27cd2
commit c614dd5
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/python/llm/src/ipex_llm/transformers/npu_model.py b/python/llm/src/ipex_llm/transformers/npu_model.py
@@ -121,8 +121,9 @@ def from_pretrained(cls,
                 optimize_llm(model)
                 if qtype == "sym_int8_rtn":
                     cls.load_convert(qtype, model, *args, **kwargs)
-                elif not qtype.is_floating_point:
-                    model = quantize_model(model, qtype)
+                else:
+                    if not qtype.is_floating_point:
+                        model = quantize_model(model, qtype)
                     create_npu_kernels(model)
             model = model.eval()
         except ImportError as _e: