diff --git a/src/transformers/models/got_ocr2/modeling_got_ocr2.py b/src/transformers/models/got_ocr2/modeling_got_ocr2.py
index 973597fcecdcb5..a5949a48e3f252 100644
--- a/src/transformers/models/got_ocr2/modeling_got_ocr2.py
+++ b/src/transformers/models/got_ocr2/modeling_got_ocr2.py
@@ -805,9 +805,9 @@ def forward(
         key_states = self.k_proj(hidden_states)
         value_states = self.v_proj(hidden_states)
 
-        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
-        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
-        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+        query_states = query_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
+        key_states = key_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
+        value_states = value_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
 
         if position_embeddings is None:
             logger.warning_once(
@@ -890,9 +890,9 @@ def forward(
         key_states = self.k_proj(hidden_states)
         value_states = self.v_proj(hidden_states)
 
-        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
-        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
-        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+        query_states = query_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
+        key_states = key_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
+        value_states = value_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
 
         if position_embeddings is None:
             logger.warning_once(
@@ -1014,9 +1014,9 @@ def forward(
         key_states = self.k_proj(hidden_states)
         value_states = self.v_proj(hidden_states)
 
-        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
-        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
-        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+        query_states = query_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
+        key_states = key_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
+        value_states = value_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
 
         if position_embeddings is None:
             logger.warning_once(
diff --git a/src/transformers/models/got_ocr2/processing_got_ocr2.py b/src/transformers/models/got_ocr2/processing_got_ocr2.py
index eb58667c1aed89..57eae3acd62013 100644
--- a/src/transformers/models/got_ocr2/processing_got_ocr2.py
+++ b/src/transformers/models/got_ocr2/processing_got_ocr2.py
@@ -219,14 +219,14 @@ def __call__(
             tokenizer_init_kwargs=self.tokenizer.init_kwargs,
             **kwargs,
         )
-        format = output_kwargs["text_kwargs"].pop("format", False)
-        num_image_tokens = output_kwargs["images_kwargs"].pop("num_image_tokens", 256)
+        format = output_kwargs["text_kwargs"].pop("format")
+        num_image_tokens = output_kwargs["images_kwargs"].pop("num_image_tokens")
         box = output_kwargs["images_kwargs"].pop("box", [None])
         color = output_kwargs["images_kwargs"].pop("color", None)
-        multi_page = output_kwargs["images_kwargs"].pop("multi_page", False)
-        crop_to_patches = output_kwargs["images_kwargs"].pop("crop_to_patches", False)
-        min_patches = output_kwargs["images_kwargs"].pop("min_patches", 1)
-        max_patches = output_kwargs["images_kwargs"].pop("max_patches", 6)
+        multi_page = output_kwargs["images_kwargs"].pop("multi_page")
+        crop_to_patches = output_kwargs["images_kwargs"].pop("crop_to_patches")
+        min_patches = output_kwargs["images_kwargs"].pop("min_patches")
+        max_patches = output_kwargs["images_kwargs"].pop("max_patches")
 
         self._check_call_arguments(images, box, color, multi_page, crop_to_patches)
         images, text, box, color = self._make_list_of_inputs(images, text, box, color, multi_page)