"to be not" -> "not to be" (#32636)

* "to be not" -> "not to be"

* Update sam.md

* Update trainer.py

* Update modeling_utils.py

* Update test_modeling_utils.py

* Update test_modeling_utils.py

docs/source/en/model_doc/sam.md

@@ -34,7 +34,7 @@ Tips:
 - The model predicts much better results if input 2D points and/or input bounding boxes are provided
 - You can prompt multiple points for the same image, and predict a single mask. 
 - Fine-tuning the model is not supported yet
-- According to the paper, textual input should be also supported. However, at this time of writing this seems to be not supported according to [the official repository](https://github.com/facebookresearch/segment-anything/issues/4#issuecomment-1497626844). 
+- According to the paper, textual input should be also supported. However, at this time of writing this seems not to be supported according to [the official repository](https://github.com/facebookresearch/segment-anything/issues/4#issuecomment-1497626844). 
 
 
 This model was contributed by [ybelkada](https://huggingface.co/ybelkada) and [ArthurZ](https://huggingface.co/ArthurZ).

src/transformers/modeling_utils.py

@@ -3034,7 +3034,7 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
             > Parameters for big model inference
 
             low_cpu_mem_usage(`bool`, *optional*):
-                Tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
+                Tries not to use more than 1x model size in CPU memory (including peak memory) while loading the model.
                 Generally should be combined with a `device_map` (such as `"auto"`) for best results.
                 This is an experimental feature and a subject to change at any moment.
                 </Tip>

src/transformers/trainer.py

@@ -2373,7 +2373,7 @@ class Trainer:
                     break
             if step < 0:
                 logger.warning(
-                    "There seems to be not a single sample in your epoch_iterator, stopping training at step"
+                    "There seems not to be a single sample in your epoch_iterator, stopping training at step"
                     f" {self.state.global_step}! This is expected if you're using an IterableDataset and set"
                     f" num_steps ({max_steps}) higher than the number of available samples."
                 )

tests/models/bloom/test_modeling_bloom.py

@@ -344,7 +344,7 @@ class BloomModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi
     fx_compatible = True
     test_missing_keys = False
     test_pruning = False
-    test_torchscript = True  # torch.autograd functions seems to be not supported
+    test_torchscript = True  # torch.autograd functions seems not to be supported
 
     def setUp(self):
         self.model_tester = BloomModelTester(self)

tests/utils/test_modeling_utils.py

@@ -2428,7 +2428,7 @@ class TestAttentionImplementation(unittest.TestCase):
                 "hf-internal-testing/tiny-random-GPTBigCodeModel", attn_implementation="flash_attention_2"
             )
 
-        self.assertTrue("the package flash_attn seems to be not installed" in str(cm.exception))
+        self.assertTrue("the package flash_attn seems not to be installed" in str(cm.exception))
 
     def test_not_available_flash_with_config(self):
         if is_flash_attn_2_available():
@@ -2443,7 +2443,7 @@ class TestAttentionImplementation(unittest.TestCase):
                 attn_implementation="flash_attention_2",
             )
 
-        self.assertTrue("the package flash_attn seems to be not installed" in str(cm.exception))
+        self.assertTrue("the package flash_attn seems not to be installed" in str(cm.exception))
 
     def test_not_available_sdpa(self):
         if is_torch_sdpa_available():