Update `InstructBlipModelIntegrationTest` (#24490)

* fix

* fix

---------
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

tests/models/instructblip/test_modeling_instructblip.py

@@ -521,6 +521,8 @@ def prepare_img():
 @require_torch
 @slow
 class InstructBlipModelIntegrationTest(unittest.TestCase):
+    # TODO (@Younes): Re-enable this when 8-bit or 4-bit is implemented.
+    @unittest.skip(reason="GPU OOM")
     def test_inference_vicuna_7b(self):
         processor = InstructBlipProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b")
         model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b").to(
@@ -596,10 +598,10 @@ class InstructBlipModelIntegrationTest(unittest.TestCase):
         generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0]
 
         # fmt: off
-        expected_outputs = [0, 37, 1023, 9850, 7, 3, 9, 388, 3575, 53, 4954, 30, 8, 223, 13, 3, 9, 4459, 4049, 16, 8, 2214, 13, 3, 9, 3164, 690, 2815, 5, 37, 388, 19, 5119, 3, 9, 4459, 8677, 28, 3, 9, 4459, 6177, 6, 11, 3, 88, 19, 3609, 46, 3575, 53, 1476, 16, 80, 609, 11, 3, 9, 3116, 13, 28958, 16, 8, 119, 5, 37, 1023, 19, 7225, 250, 34, 1267, 3, 9, 388, 692, 10428, 16, 8, 2214, 13, 3, 9, 3164, 690, 2815, 5, 94, 19, 487, 24, 8, 388, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 5, 611, 6, 34, 19, 92, 487, 24, 8, 388, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 5, 86, 48, 495, 6, 8, 388, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 5, 216, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 5, 4063, 6, 8, 388, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 5, 1875, 8, 388, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 6, 34, 19, 487, 24, 3, 88, 47, 88, 26, 112, 4954, 16, 8, 223, 13, 8, 4049, 12, 1097, 97, 383, 112, 161, 1135, 5, 1]
+        expected_outputs = [0, 37, 1023, 9850, 7, 3, 9, 388, 3575, 53, 4954, 30, 8, 223, 13, 3, 9, 4459, 4049, 16, 8, 2214, 13, 3, 9, 3164, 690, 2815, 5, 37, 388, 19, 5119, 3, 9, 4459, 8677, 28, 3, 9, 2756, 4459, 6177, 6, 11, 3, 88, 19, 338, 46, 3575, 53, 1476, 12, 743, 112, 2491, 5, 37, 1023, 19, 7225, 788, 12, 8, 685, 24, 34, 1267, 3, 9, 388, 3575, 53, 4954, 30, 8, 223, 13, 3, 9, 4049, 16, 8, 2214, 13, 3, 9, 3164, 690, 2815, 5, 94, 19, 487, 24, 8, 388, 19, 1119, 12, 1097, 540, 57, 692, 112, 10428, 30, 8, 223, 13, 8, 4049, 6, 68, 34, 19, 92, 487, 24, 3, 88, 19, 1119, 12, 1097, 97, 57, 692, 112, 10428, 30, 8, 223, 13, 8, 4049, 16, 8, 2214, 13, 3, 9, 3164, 690, 2815, 5, 3, 13865, 13, 8, 1053, 21, 8, 388, 31, 7, 2874, 6, 34, 19, 964, 24, 3, 88, 19, 1119, 12, 1097, 97, 57, 692, 112, 10428, 30, 8, 223, 13, 8, 4049, 16, 8, 2214, 13, 3, 9, 3164, 690, 2815, 5, 1]
         # fmt: on
         self.assertEqual(outputs[0].tolist(), expected_outputs)
         self.assertEqual(
             generated_text,
-            "The image depicts a man ironing clothes on the back of a yellow van in the middle of a busy city street. The man is wearing a yellow shirt with a yellow tie, and he is holding an ironing board in one hand and a pair of scissors in the other. The image is unusual because it shows a man doing laundry in the middle of a busy city street. It is possible that the man washed his clothes in the back of the van to save time during his workday. However, it is also possible that the man washed his clothes in the back of the van to save time during his workday. In this case, the man washed his clothes in the back of the van to save time during his workday. He washed his clothes in the back of the van to save time during his workday. Therefore, the man washed his clothes in the back of the van to save time during his workday. Although the man washed his clothes in the back of the van to save time during his workday, it is possible that he washed his clothes in the back of the van to save time during his workday.",
+            "The image depicts a man ironing clothes on the back of a yellow van in the middle of a busy city street. The man is wearing a yellow shirt with a bright yellow tie, and he is using an ironing board to complete his task. The image is unusual due to the fact that it shows a man ironing clothes on the back of a van in the middle of a busy city street. It is possible that the man is trying to save money by doing his laundry on the back of the van, but it is also possible that he is trying to save time by doing his laundry on the back of the van in the middle of a busy city street. Regardless of the reason for the man's actions, it is clear that he is trying to save time by doing his laundry on the back of the van in the middle of a busy city street.",
         )