[tests] fix the wrong output in...

[tests] fix the wrong output in `ImageToTextPipelineTests.test_conditional_generation_llava` (#29975)

bug fix

tests/pipelines/test_pipelines_image_to_text.py

@@ -290,7 +290,7 @@ class ImageToTextPipelineTests(unittest.TestCase):
             outputs,
             [
                 {
-                    "generated_text": "<image> \nUSER: What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud?\nASSISTANT: Lava"
+                    "generated_text": "\nUSER: What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud?\nASSISTANT: Lava"
                 }
             ],
         )