Enable SIM rules

Signed-off-by: cyy <[email protected]>

Author: cyyever

examples/modular-transformers/modeling_dummy_bert.py

@@ -302,9 +302,7 @@ def forward(
         # in SDPA to support both torch.compile's dynamic shapes and full graph options. An inline conditional prevents dynamic shapes from compiling.
         # The tgt_len > 1 is necessary to match with AttentionMaskConverter.to_causal_4d that does not create
         # a causal mask in case tgt_len == 1.
-        is_causal = (
-            True if self.is_decoder and not is_cross_attention and attention_mask is None and tgt_len > 1 else False
-        )
+        is_causal = self.is_decoder and not is_cross_attention and attention_mask is None and tgt_len > 1
 
         attn_output = torch.nn.functional.scaled_dot_product_attention(
             query_layer,

examples/modular-transformers/modeling_roberta.py

@@ -305,9 +305,7 @@ def forward(
         # in SDPA to support both torch.compile's dynamic shapes and full graph options. An inline conditional prevents dynamic shapes from compiling.
         # The tgt_len > 1 is necessary to match with AttentionMaskConverter.to_causal_4d that does not create
         # a causal mask in case tgt_len == 1.
-        is_causal = (
-            True if self.is_decoder and not is_cross_attention and attention_mask is None and tgt_len > 1 else False
-        )
+        is_causal = self.is_decoder and not is_cross_attention and attention_mask is None and tgt_len > 1
 
         attn_output = torch.nn.functional.scaled_dot_product_attention(
             query_layer,

pyproject.toml

@@ -19,10 +19,13 @@ line-length = 119
 
 [tool.ruff.lint]
 # Never enforce `E501` (line length violations).
-ignore = ["C901", "E501", "E741", "F402", "F823"]
+# SIM300: Yoda condition detected
+# SIM212: Checks for if expressions that check against a negated condition.
+# SIM905: Consider using a list literal instead of `str.split`
+ignore = ["C901", "E501", "E741", "F402", "F823", "SIM1", "SIM300", "SIM212", "SIM905"]
 # 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", "PERF102", "PLC1802", "PLC0208"]
+select = ["C", "E", "F", "I", "W", "RUF013", "UP006", "PERF102", "PLC1802", "PLC0208","SIM"]
 extend-safe-fixes = ["UP006"]
 
 # Ignore import violations in all `__init__.py` files.

src/transformers/commands/serving.py

@@ -891,7 +891,7 @@ def generate_chat_completion(self, req: dict) -> Generator[str, None, None]:
         inputs = processor.apply_chat_template(
             processor_inputs,
             add_generation_prompt=True,
-            tools=req.get("tools", None),
+            tools=req.get("tools"),
             return_tensors="pt",
             return_dict=True,
             tokenize=True,

src/transformers/data/data_collator.py

@@ -183,7 +183,7 @@ def tf_default_data_collator(features: list[InputDataClass]) -> dict[str, Any]:
     if label_col_name is not None:
         if isinstance(first[label_col_name], tf.Tensor):
             dtype = tf.int64 if first[label_col_name].dtype.is_integer else tf.float32
-        elif isinstance(first[label_col_name], np.ndarray) or isinstance(first[label_col_name], np.generic):
+        elif isinstance(first[label_col_name], (np.ndarray, np.generic)):
             dtype = tf.int64 if np.issubdtype(first[label_col_name].dtype, np.integer) else tf.float32
         elif isinstance(first[label_col_name], (tuple, list)):
             dtype = tf.int64 if isinstance(first[label_col_name][0], int) else tf.float32

src/transformers/generation/utils.py

@@ -645,8 +645,8 @@ def prepare_inputs_for_generation(
 
             # If it's not defined, it means the model uses the new general mask API
             if causal_mask_creation_function is None:  # can't be found
-                token_type_ids = model_inputs.get("token_type_ids", None)
-                position_ids = model_inputs.get(position_ids_key, None)
+                token_type_ids = model_inputs.get("token_type_ids")
+                position_ids = model_inputs.get(position_ids_key)
                 # Some models may overwrite the general one
                 causal_mask_creation_function = getattr(self, "create_masks_for_generate", create_masks_for_generate)
                 attention_mask = causal_mask_creation_function(

src/transformers/integrations/flex_attention.py

@@ -277,7 +277,7 @@ def score_mod(score, batch_idx, head_idx, q_idx, kv_idx):
     num_local_query_heads = query.shape[1]
 
     # When running TP this helps:
-    if not ((num_local_query_heads & (num_local_query_heads - 1)) == 0):
+    if (num_local_query_heads & (num_local_query_heads - 1)) != 0:
         key = repeat_kv(key, query.shape[1] // key.shape[1])
         value = repeat_kv(value, query.shape[1] // value.shape[1])
         enable_gqa = False

src/transformers/integrations/vptq.py

@@ -45,7 +45,7 @@ def replace_with_vptq_linear(
             should not be passed by the user.
     """
 
-    modules_to_not_convert = ["lm_head"] if not modules_to_not_convert else modules_to_not_convert
+    modules_to_not_convert = modules_to_not_convert if modules_to_not_convert else ["lm_head"]
 
     for name, module in model.named_children():
         if current_key_name is None:

src/transformers/keras_callbacks.py

@@ -167,7 +167,7 @@ def _postprocess_predictions_or_labels(self, inputs):
             # If it's a dict with only one key, just return the array
             if len(outputs) == 1:
                 outputs = list(outputs.values())[0]
-        elif isinstance(inputs[0], list) or isinstance(inputs[0], tuple):
+        elif isinstance(inputs[0], (tuple, list)):
             outputs = []
             for input_list in zip(*inputs):
                 outputs.append(self._concatenate_batches(input_list))

src/transformers/models/biogpt/convert_biogpt_original_pytorch_checkpoint_to_pytorch.py

@@ -148,7 +148,7 @@ def rewrite_dict_keys(d):
     # (1) remove word breaking symbol, (2) add word ending symbol where the word is not broken up,
     # e.g.: d = {'le@@': 5, 'tt@@': 6, 'er': 7} => {'le': 5, 'tt': 6, 'er</w>': 7}
     d2 = dict((re.sub(r"@@$", "", k), v) if k.endswith("@@") else (re.sub(r"$", "</w>", k), v) for k, v in d.items())
-    keep_keys = "<s> <pad> </s> <unk>".split()
+    keep_keys = ["<s>", "<pad>", "</s>", "<unk>"]
     # restore the special tokens
     for k in keep_keys:
         del d2[f"{k}</w>"]