[pre-commit.ci] pre-commit autoupdate (#5572)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/PyCQA/autoflake: v2.2.1 → v2.3.1](https://github.com/PyCQA/autoflake/compare/v2.2.1...v2.3.1)
- [github.com/pycqa/isort: 5.12.0 → 5.13.2](https://github.com/pycqa/isort/compare/5.12.0...5.13.2)
- [github.com/psf/black-pre-commit-mirror: 23.9.1 → 24.4.2](https://github.com/psf/black-pre-commit-mirror/compare/23.9.1...24.4.2)
- [github.com/pre-commit/mirrors-clang-format: v13.0.1 → v18.1.7](https://github.com/pre-commit/mirrors-clang-format/compare/v13.0.1...v18.1.7)
- [github.com/pre-commit/pre-commit-hooks: v4.3.0 → v4.6.0](https://github.com/pre-commit/pre-commit-hooks/compare/v4.3.0...v4.6.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

applications/ColossalEval/colossal_eval/dataset/agieval.py

@@ -78,7 +78,9 @@ def get_prompt(line: Dict, dataset_name: str, logger: DistributedLogger) -> Dict
             option_string = "ABCDEFG"
             count = len(line["options"])
 
-            input = "问题：" + line["question"] + " " + "从以下选项中选择：" + " ".join(line["options"]) + "\n" + "答案："
+            input = (
+                "问题：" + line["question"] + " " + "从以下选项中选择：" + " ".join(line["options"]) + "\n" + "答案："
+            )
 
             all_classes = list(option_string[0:count])
 
@@ -150,7 +152,15 @@ def combine_prompt(prompt_path, dataset_name, load_explanation=True, chat_mode=F
             )
         elif dataset_name in chinese_qa_datasets:
             question_input = (
-                "问题：" + passage + " " + question + "\n" + "从以下选项中选择：" + " ".join(options) + "\n" + "答案：{}".format(label)
+                "问题："
+                + passage
+                + " "
+                + question
+                + "\n"
+                + "从以下选项中选择："
+                + " ".join(options)
+                + "\n"
+                + "答案：{}".format(label)
             )
         elif dataset_name in english_cloze_datasets:
             question_input = "Question: ".format(idx + 1) + question + "\n" + "Answer: {}".format(answer)

applications/ColossalEval/colossal_eval/dataset/ceval.py

@@ -57,7 +57,11 @@ ceval_subject_mapping = {
     "urban_and_rural_planner": ["Urban and Rural Planner", "注册城乡规划师", "Other"],
     "accountant": ["Accountant", "注册会计师", "Other"],
     "fire_engineer": ["Fire Engineer", "注册消防工程师", "Other"],
-    "environmental_impact_assessment_engineer": ["Environmental Impact Assessment Engineer", "环境影响评价工程师", "Other"],
+    "environmental_impact_assessment_engineer": [
+        "Environmental Impact Assessment Engineer",
+        "环境影响评价工程师",
+        "Other",
+    ],
     "tax_accountant": ["Tax Accountant", "税务师", "Other"],
     "physician": ["Physician", "医师资格", "Other"],
 }

applications/ColossalEval/colossal_eval/dataset/mtbench.py

@@ -56,9 +56,11 @@ class MTBenchDataset(BaseDataset):
                     "instruction": question["turns"],
                     "input": "",
                     "output": [],
-                    "target": [""] * turn_number
-                    if question["question_id"] not in reference
-                    else reference[question["question_id"]],
+                    "target": (
+                        [""] * turn_number
+                        if question["question_id"] not in reference
+                        else reference[question["question_id"]]
+                    ),
                 }
 
                 if category in dataset["test"]:

applications/ColossalEval/colossal_eval/models/huggingface.py

@@ -77,7 +77,9 @@ class HuggingFaceModel(BaseModel):
             self.indices_for_choices[0].append(
                 self.tokenizer(f"Answer: {choice}", add_special_tokens=False).input_ids[-1]
             )
-            self.indices_for_choices[1].append(self.tokenizer(f"答案：{choice}", add_special_tokens=False).input_ids[-1])
+            self.indices_for_choices[1].append(
+                self.tokenizer(f"答案：{choice}", add_special_tokens=False).input_ids[-1]
+            )
 
     def _load_tokenizer(self, path: str, tokenizer_path: Optional[str], tokenizer_kwargs: dict):
         """