fix check_model_inputs

README.md

@@ -60,9 +60,6 @@ temperature = 0.8
 
 ### Serving
 
-> [!IMPORTANT]
-> Running a trillion-parameter model using the native Hugging Face forward method is challenging. We strongly recommend using an LLM inference engine (such as LMDeploy, vLLM, or sglang) to host Intern-S1-Pro and accessing the model via API.
-
 Intern-S1-Pro can be deployed using any of the following LLM inference frameworks:
 
 - LMDeploy

modeling_interns1_pro.py

@@ -986,7 +986,7 @@ class InternS1ProTextModel(InternS1ProPreTrainedModel):
         # Initialize weights and apply final processing
         self.post_init()
 
-    @check_model_inputs
+    @check_model_inputs()
     @auto_docstring
     def forward(
         self,
@@ -1212,7 +1212,7 @@ class InternS1ProModel(InternS1ProPreTrainedModel):
         return special_image_mask, special_video_mask
 
     @auto_docstring
-    @check_model_inputs
+    @check_model_inputs()
     def forward(
         self,
         input_ids: torch.LongTensor = None,
@@ -1405,7 +1405,7 @@ class InternS1ProForConditionalGeneration(InternS1ProPreTrainedModel, Generation
     def visual(self):
         return self.model.visual
 
-    @check_model_inputs
+    @check_model_inputs()
     def forward(
         self,
         input_ids: torch.LongTensor = None,