diff --git a/examples/pytorch/3d_parallel_checks.py b/examples/pytorch/3d_parallel_checks.py index 792a7c8c1655..944caad72f3f 100644 --- a/examples/pytorch/3d_parallel_checks.py +++ b/examples/pytorch/3d_parallel_checks.py @@ -754,9 +754,9 @@ def get_parameters(model: nn.Module) -> Iterable[torch.Tensor]: Returns: Iterable[torch.Tensor]: An iterator over all parameters in the model """ - for name, module in model._modules.items(): + for module in model._modules.values(): # Look for parameters in module attributes - for attr_name, attr in module.__dict__.items(): + for attr in module.__dict__.values(): if isinstance(attr, torch.Tensor) and attr.requires_grad: yield attr # Recursively get parameters from submodules diff --git a/pyproject.toml b/pyproject.toml index 4e7a0c62d0fc..83a4bf3ad3c0 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -19,10 +19,10 @@ line-length = 119 [tool.ruff.lint] # Never enforce `E501` (line length violations). -ignore = ["C901", "E501", "E741", "F402", "F823" ] +ignore = ["C901", "E501", "E741", "F402", "F823"] # RUF013: Checks for the use of implicit Optional # in type annotations when the default parameter value is None. -select = ["C", "E", "F", "I", "W", "RUF013", "UP006"] +select = ["C", "E", "F", "I", "W", "RUF013", "UP006", "PERF102", "PLC1802", "PLC0208"] extend-safe-fixes = ["UP006"] # Ignore import violations in all `__init__.py` files. diff --git a/src/transformers/configuration_utils.py b/src/transformers/configuration_utils.py index e0f71dce134e..32a3b57956ca 100755 --- a/src/transformers/configuration_utils.py +++ b/src/transformers/configuration_utils.py @@ -607,7 +607,7 @@ def from_pretrained( if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type: # sometimes the config has no `base_config_key` if the config is used in several composite models # e.g. LlamaConfig. In that case we try to see if there is match in `model_type` before raising a warning - for k, v in config_dict.items(): + for v in config_dict.values(): if isinstance(v, dict) and v.get("model_type") == cls.model_type: config_dict = v diff --git a/src/transformers/modeling_utils.py b/src/transformers/modeling_utils.py index 6fadc8adf1e5..4672af716527 100644 --- a/src/transformers/modeling_utils.py +++ b/src/transformers/modeling_utils.py @@ -2166,7 +2166,7 @@ def post_init(self): self._tp_plan.update({f"{name}.{k}": v for k, v in plan.copy().items()}) if self._tp_plan is not None and is_torch_greater_or_equal("2.5") and _torch_distributed_available: - for _, v in self._tp_plan.items(): + for v in self._tp_plan.values(): if v not in ALL_PARALLEL_STYLES: raise ValueError( f"Unsupported tensor parallel style {v}. Supported styles are {ALL_PARALLEL_STYLES}" @@ -2845,7 +2845,7 @@ def tie_encoder_to_decoder_recursively( all_encoder_weights = {module_name + "/" + sub_name for sub_name in encoder_modules.keys()} encoder_layer_pos = 0 - for name, module in decoder_modules.items(): + for name in decoder_modules.keys(): if name.isdigit(): encoder_name = str(int(name) + encoder_layer_pos) decoder_name = name @@ -5830,7 +5830,7 @@ def caching_allocator_warmup(model: PreTrainedModel, expanded_device_map: dict, accelerator_device_map = { param: torch.device(device) for param, device in expanded_device_map.items() if is_accelerator_device(device) } - if not len(accelerator_device_map): + if not accelerator_device_map: return tp_plan_regex = ( diff --git a/src/transformers/models/auto/feature_extraction_auto.py b/src/transformers/models/auto/feature_extraction_auto.py index 3595de53bbda..fcc93165de83 100644 --- a/src/transformers/models/auto/feature_extraction_auto.py +++ b/src/transformers/models/auto/feature_extraction_auto.py @@ -133,7 +133,7 @@ def feature_extractor_class_from_name(class_name: str): except AttributeError: continue - for _, extractor in FEATURE_EXTRACTOR_MAPPING._extra_content.items(): + for extractor in FEATURE_EXTRACTOR_MAPPING._extra_content.values(): if getattr(extractor, "__name__", None) == class_name: return extractor diff --git a/src/transformers/models/auto/image_processing_auto.py b/src/transformers/models/auto/image_processing_auto.py index c2ee5ffe5934..d3c4367eca51 100644 --- a/src/transformers/models/auto/image_processing_auto.py +++ b/src/transformers/models/auto/image_processing_auto.py @@ -212,7 +212,7 @@ def get_image_processor_class_from_name(class_name: str): except AttributeError: continue - for _, extractors in IMAGE_PROCESSOR_MAPPING._extra_content.items(): + for extractors in IMAGE_PROCESSOR_MAPPING._extra_content.values(): for extractor in extractors: if getattr(extractor, "__name__", None) == class_name: return extractor @@ -533,7 +533,7 @@ def from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs): ) use_fast = False if use_fast: - for _, image_processors in IMAGE_PROCESSOR_MAPPING_NAMES.items(): + for image_processors in IMAGE_PROCESSOR_MAPPING_NAMES.values(): if image_processor_type in image_processors: break else: diff --git a/src/transformers/models/auto/tokenization_auto.py b/src/transformers/models/auto/tokenization_auto.py index 0543bfd062af..9dd78dbeae40 100644 --- a/src/transformers/models/auto/tokenization_auto.py +++ b/src/transformers/models/auto/tokenization_auto.py @@ -744,7 +744,7 @@ def tokenizer_class_from_name(class_name: str) -> Union[type[Any], None]: except AttributeError: continue - for config, tokenizers in TOKENIZER_MAPPING._extra_content.items(): + for tokenizers in TOKENIZER_MAPPING._extra_content.values(): for tokenizer in tokenizers: if getattr(tokenizer, "__name__", None) == class_name: return tokenizer diff --git a/src/transformers/models/auto/video_processing_auto.py b/src/transformers/models/auto/video_processing_auto.py index 2bd2d86719b0..619d67c561f8 100644 --- a/src/transformers/models/auto/video_processing_auto.py +++ b/src/transformers/models/auto/video_processing_auto.py @@ -84,7 +84,7 @@ def video_processor_class_from_name(class_name: str): except AttributeError: continue - for _, extractor in VIDEO_PROCESSOR_MAPPING._extra_content.items(): + for extractor in VIDEO_PROCESSOR_MAPPING._extra_content.values(): if getattr(extractor, "__name__", None) == class_name: return extractor diff --git a/src/transformers/models/bridgetower/modeling_bridgetower.py b/src/transformers/models/bridgetower/modeling_bridgetower.py index 42d85da5e506..3b8313e31e8b 100644 --- a/src/transformers/models/bridgetower/modeling_bridgetower.py +++ b/src/transformers/models/bridgetower/modeling_bridgetower.py @@ -140,7 +140,7 @@ def attention(self, hidden_state: torch.Tensor, attention_mask: torch.Tensor): def forward(self, hidden_state: torch.Tensor, attention_mask: Optional[torch.Tensor] = None): residual_state = hidden_state + self.attention(self.ln_1(hidden_state), attention_mask) hidden_state = self.ln_2(residual_state) - for _, layer in self.mlp.items(): + for layer in self.mlp.values(): hidden_state = layer(hidden_state) hidden_state = residual_state + hidden_state return hidden_state diff --git a/src/transformers/models/donut/processing_donut.py b/src/transformers/models/donut/processing_donut.py index edadc7b12678..0e39528c7c07 100644 --- a/src/transformers/models/donut/processing_donut.py +++ b/src/transformers/models/donut/processing_donut.py @@ -199,7 +199,7 @@ def token2json(self, tokens, is_inner_value=False, added_vocab=None): if tokens[:6] == r"": # non-leaf nodes return [output] + self.token2json(tokens[6:], is_inner_value=True, added_vocab=added_vocab) - if len(output): + if output: return [output] if is_inner_value else output else: return [] if is_inner_value else {"text_sequence": tokens} diff --git a/src/transformers/models/grounding_dino/convert_grounding_dino_to_hf.py b/src/transformers/models/grounding_dino/convert_grounding_dino_to_hf.py index 84998cfdefa8..9f3f70bc57ad 100644 --- a/src/transformers/models/grounding_dino/convert_grounding_dino_to_hf.py +++ b/src/transformers/models/grounding_dino/convert_grounding_dino_to_hf.py @@ -239,7 +239,7 @@ def create_rename_keys(state_dict, config): ########################################## DECODER - END ########################################## Additional - START - for layer_name, params in state_dict.items(): + for layer_name in state_dict.keys(): #### TEXT BACKBONE if "bert" in layer_name: rename_keys.append((layer_name, layer_name.replace("bert", "model.text_backbone"))) diff --git a/src/transformers/models/llama4/image_processing_llama4_fast.py b/src/transformers/models/llama4/image_processing_llama4_fast.py index fc76a013c90d..257893980111 100644 --- a/src/transformers/models/llama4/image_processing_llama4_fast.py +++ b/src/transformers/models/llama4/image_processing_llama4_fast.py @@ -177,7 +177,7 @@ def find_supported_resolutions(max_num_chunks: int, patch_size: SizeDict) -> tor # get the resolutions multiplied by the patch_size possible_resolutions = [] - for key, value in asp_dict.items(): + for value in asp_dict.values(): for height, depth in value: possible_resolutions.append((height * patch_size, depth * patch_size)) diff --git a/src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py index 1881e26e1555..1edcae80f67f 100644 --- a/src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py @@ -100,7 +100,7 @@ def convert_luke_checkpoint(checkpoint_path, metadata_path, entity_vocab_path, p state_dict.pop("lm_head.decoder.weight") state_dict.pop("lm_head.decoder.bias") state_dict_for_hugging_face = OrderedDict() - for key, value in state_dict.items(): + for key in state_dict.keys(): if not (key.startswith("lm_head") or key.startswith("entity_predictions")): state_dict_for_hugging_face[f"luke.{key}"] = state_dict[key] else: diff --git a/src/transformers/models/omdet_turbo/convert_omdet_turbo_to_hf.py b/src/transformers/models/omdet_turbo/convert_omdet_turbo_to_hf.py index 6ee52db488e8..e4e31e4d8ae6 100644 --- a/src/transformers/models/omdet_turbo/convert_omdet_turbo_to_hf.py +++ b/src/transformers/models/omdet_turbo/convert_omdet_turbo_to_hf.py @@ -100,7 +100,7 @@ def create_rename_keys_vision(state_dict, config): ########################################## VISION BACKBONE - END ########################################## ENCODER - START - for layer_name, params in state_dict.items(): + for layer_name in state_dict.keys(): if "neck" in layer_name: layer_name_replace = layer_name.replace("neck", "encoder") layer_name_replace = layer_name_replace.replace("input_proj", "channel_projection_layers") @@ -117,7 +117,7 @@ def create_rename_keys_vision(state_dict, config): ########################################## ENCODER - END ########################################## DECODER - START - for layer_name, params in state_dict.items(): + for layer_name in state_dict.keys(): if layer_name.startswith("decoder"): layer_name_replace = layer_name.replace("decoder.decoder.layers", "decoder.layers") layer_name_replace = layer_name_replace.replace("input_proj", "channel_projection_layers") diff --git a/src/transformers/models/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py index 6352b7130055..d43c05cd6220 100644 --- a/src/transformers/models/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py @@ -144,7 +144,7 @@ def convert_xmod_checkpoint_to_pytorch( if sorted(bert_output.adapter_modules.keys()) != sorted(xmod_layer.adapter_modules.keys()): raise AssertionError("Lists of language adapters do not match.") - for lang_code, adapter in xmod_layer.adapter_modules.items(): + for lang_code in xmod_layer.adapter_modules.keys(): to_adapter = bert_output.adapter_modules[lang_code] from_adapter = xmod_layer.adapter_modules[lang_code] to_adapter.dense1.weight = from_adapter.fc1.weight diff --git a/src/transformers/models/zoedepth/convert_zoedepth_to_hf.py b/src/transformers/models/zoedepth/convert_zoedepth_to_hf.py index cbf47a636b7d..81fcb66afa3d 100644 --- a/src/transformers/models/zoedepth/convert_zoedepth_to_hf.py +++ b/src/transformers/models/zoedepth/convert_zoedepth_to_hf.py @@ -266,7 +266,7 @@ def convert_state_dict(orig_state_dict): def remove_ignore_keys(state_dict): - for key, _ in state_dict.copy().items(): + for key in state_dict.copy().keys(): if ( "fc_norm" in key or "relative_position_index" in key diff --git a/src/transformers/pipelines/base.py b/src/transformers/pipelines/base.py index 907746756822..238467ee292e 100644 --- a/src/transformers/pipelines/base.py +++ b/src/transformers/pipelines/base.py @@ -1288,14 +1288,14 @@ def check_model_type(self, supported_models: Union[list[str], dict]): if self.task in SUPPORTED_PEFT_TASKS: supported_models_names.extend(SUPPORTED_PEFT_TASKS[self.task]) - for _, model_name in supported_models.items(): + for model_name in supported_models.values(): # Mapping can now contain tuples of models for the same configuration. if isinstance(model_name, tuple): supported_models_names.extend(list(model_name)) else: supported_models_names.append(model_name) if hasattr(supported_models, "_model_mapping"): - for _, model in supported_models._model_mapping._extra_content.items(): + for model in supported_models._model_mapping._extra_content.values(): if isinstance(model_name, tuple): supported_models_names.extend([m.__name__ for m in model]) else: diff --git a/src/transformers/tokenization_utils_base.py b/src/transformers/tokenization_utils_base.py index 7dc1ac124457..2e8dfd196ccc 100644 --- a/src/transformers/tokenization_utils_base.py +++ b/src/transformers/tokenization_utils_base.py @@ -232,7 +232,7 @@ def __init__( self._encodings = encoding - if n_sequences is None and encoding is not None and len(encoding): + if n_sequences is None and encoding is not None and encoding: n_sequences = encoding[0].n_sequences self._n_sequences = n_sequences diff --git a/src/transformers/trainer_pt_utils.py b/src/transformers/trainer_pt_utils.py index 2fb362605855..84f65c954460 100644 --- a/src/transformers/trainer_pt_utils.py +++ b/src/transformers/trainer_pt_utils.py @@ -149,7 +149,7 @@ def find_batch_size(tensors): if result is not None: return result elif isinstance(tensors, Mapping): - for key, value in tensors.items(): + for value in tensors.values(): result = find_batch_size(value) if result is not None: return result diff --git a/src/transformers/utils/import_utils.py b/src/transformers/utils/import_utils.py index 251c2309edfd..93c4d971ac37 100644 --- a/src/transformers/utils/import_utils.py +++ b/src/transformers/utils/import_utils.py @@ -2183,12 +2183,12 @@ def __init__( self._modules = self._modules.union(module_keys) for key, values in module.items(): - if len(missing_backends): + if missing_backends: self._object_missing_backend[key] = missing_backends for value in values: self._class_to_module[value] = key - if len(missing_backends): + if missing_backends: self._object_missing_backend[value] = missing_backends _import_structure.setdefault(key, []).extend(values) diff --git a/src/transformers/utils/quantization_config.py b/src/transformers/utils/quantization_config.py index 10ae5f92e4ac..70c0b034a541 100644 --- a/src/transformers/utils/quantization_config.py +++ b/src/transformers/utils/quantization_config.py @@ -1199,7 +1199,7 @@ def post_init(self): r""" Safety checker that arguments are correct """ - for layer_name, layer_param in self.config_for_layers.items(): + for layer_param in self.config_for_layers.values(): VptqLayerConfig(**layer_param) if self.enable_proxy_error is True: raise ValueError("enable_proxy_error should always be False until we support training") diff --git a/tests/models/auto/test_modeling_auto.py b/tests/models/auto/test_modeling_auto.py index cfc0191c02b3..876d1b9cad5a 100644 --- a/tests/models/auto/test_modeling_auto.py +++ b/tests/models/auto/test_modeling_auto.py @@ -125,7 +125,7 @@ def test_model_for_pretraining_from_pretrained(self): self.assertIsNotNone(model) self.assertIsInstance(model, BertForPreTraining) # Only one value should not be initialized and in the missing keys. - for key, value in loading_info.items(): + for value in loading_info.values(): self.assertEqual(len(value), 0) @slow diff --git a/tests/models/auto/test_tokenization_auto.py b/tests/models/auto/test_tokenization_auto.py index 5d6c4254785f..673963129411 100644 --- a/tests/models/auto/test_tokenization_auto.py +++ b/tests/models/auto/test_tokenization_auto.py @@ -70,7 +70,7 @@ def setUp(self): @slow def test_tokenizer_from_pretrained(self): - for model_name in {"google-bert/bert-base-uncased", "google-bert/bert-base-cased"}: + for model_name in ("google-bert/bert-base-uncased", "google-bert/bert-base-cased"): tokenizer = AutoTokenizer.from_pretrained(model_name) self.assertIsNotNone(tokenizer) self.assertIsInstance(tokenizer, (BertTokenizer, BertTokenizerFast)) diff --git a/tests/models/luke/test_modeling_luke.py b/tests/models/luke/test_modeling_luke.py index dd51475540c7..7cc282e49ab0 100644 --- a/tests/models/luke/test_modeling_luke.py +++ b/tests/models/luke/test_modeling_luke.py @@ -897,7 +897,7 @@ def test_inference_base_model(self): encoding = tokenizer(text, entity_spans=[span], add_prefix_space=True, return_tensors="pt") # move all values to device - for key, value in encoding.items(): + for key in encoding.keys(): encoding[key] = encoding[key].to(torch_device) outputs = model(**encoding) @@ -932,7 +932,7 @@ def test_inference_large_model(self): encoding = tokenizer(text, entity_spans=[span], add_prefix_space=True, return_tensors="pt") # move all values to device - for key, value in encoding.items(): + for key in encoding.keys(): encoding[key] = encoding[key].to(torch_device) outputs = model(**encoding) diff --git a/tests/peft_integration/test_peft_integration.py b/tests/peft_integration/test_peft_integration.py index 7efa5252e849..0ce14f041292 100644 --- a/tests/peft_integration/test_peft_integration.py +++ b/tests/peft_integration/test_peft_integration.py @@ -757,7 +757,7 @@ def test_peft_load_adapter_training_inference_mode_false(self): model.load_adapter(tmpdirname, is_trainable=True) for name, module in model.named_modules(): - if len(list(module.children())): + if list(module.children()): # only check leaf modules continue diff --git a/tests/test_modeling_common.py b/tests/test_modeling_common.py index b33c246e7cfe..fbb8d5f541a4 100755 --- a/tests/test_modeling_common.py +++ b/tests/test_modeling_common.py @@ -2535,7 +2535,7 @@ def test_can_use_safetensors(self): shared_ptrs = {k: v for k, v in ptrs.items() if len(v) > 1} - for _, shared_names in shared_ptrs.items(): + for shared_names in shared_ptrs.values(): reloaded_ptrs = {reloaded_state[k].data_ptr() for k in shared_names} self.assertEqual( len(reloaded_ptrs), diff --git a/tests/test_pipeline_mixin.py b/tests/test_pipeline_mixin.py index f71954f76a63..2cad0b90527e 100644 --- a/tests/test_pipeline_mixin.py +++ b/tests/test_pipeline_mixin.py @@ -139,7 +139,7 @@ "zero-shot-image-classification": (ZeroShotImageClassificationPipeline, ZeroShotImageClassificationInput), } -for task, task_info in pipeline_test_mapping.items(): +for task_info in pipeline_test_mapping.values(): test = task_info["test"] task_info["mapping"] = { "pt": getattr(test, "model_mapping", None), diff --git a/tests/utils/test_import_structure.py b/tests/utils/test_import_structure.py index 87a90cae4392..d6382a5fdf11 100644 --- a/tests/utils/test_import_structure.py +++ b/tests/utils/test_import_structure.py @@ -96,7 +96,7 @@ def test_transformers_specific_model_import(self): with self.subTest(f"Testing arch {architecture}"): import_structure = define_import_structure(self.models_path / architecture) backend_agnostic_import_structure = {} - for requirement, module_object_mapping in import_structure.items(): + for module_object_mapping in import_structure.values(): for module, objects in module_object_mapping.items(): if module not in backend_agnostic_import_structure: backend_agnostic_import_structure[module] = [] diff --git a/utils/add_pipeline_model_mapping_to_test.py b/utils/add_pipeline_model_mapping_to_test.py index e67f65f824c6..f036e44495e4 100644 --- a/utils/add_pipeline_model_mapping_to_test.py +++ b/utils/add_pipeline_model_mapping_to_test.py @@ -37,7 +37,7 @@ PIPELINE_TEST_MAPPING = {} -for task, _ in pipeline_test_mapping.items(): +for task in pipeline_test_mapping.keys(): PIPELINE_TEST_MAPPING[task] = {"pt": None, "tf": None} diff --git a/utils/check_repo.py b/utils/check_repo.py index 9fcf14babb9a..5c79e0a228d8 100644 --- a/utils/check_repo.py +++ b/utils/check_repo.py @@ -790,7 +790,7 @@ def check_all_auto_object_names_being_defined(): mappings_to_check.update({name: getattr(module, name) for name in mapping_names}) for name, mapping in mappings_to_check.items(): - for _, class_names in mapping.items(): + for class_names in mapping.values(): if not isinstance(class_names, tuple): class_names = (class_names,) for class_name in class_names: diff --git a/utils/notification_service_doc_tests.py b/utils/notification_service_doc_tests.py index 2e006655ce6a..5802cf23a6eb 100644 --- a/utils/notification_service_doc_tests.py +++ b/utils/notification_service_doc_tests.py @@ -332,7 +332,7 @@ def add_path(self, path: str): doc_test_results = {} # `artifact_key` is the artifact path - for artifact_key, artifact_obj in available_artifacts.items(): + for artifact_obj in available_artifacts.values(): artifact_path = artifact_obj.paths[0] if not artifact_path["path"].startswith("doc_tests_gpu_test_reports_"): continue