Add supports_gradient_checkpointing

configuration_internvl_chat.py

@@ -63,6 +63,8 @@ class InternVLChatConfig(PretrainedConfig):
         self.ps_version = ps_version  # pixel shuffle version
         self.min_dynamic_patch = min_dynamic_patch
         self.max_dynamic_patch = max_dynamic_patch
+        # By default, we use tie_word_embeddings=False for models of all sizes.
+        self.tie_word_embeddings = self.llm_config.tie_word_embeddings
 
         logger.info(f'vision_select_layer: {self.select_layer}')
         logger.info(f'ps_version: {self.ps_version}')