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

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

applications/ColossalEval/colossal_eval/dataset/agieval.py

@@ -197,9 +197,7 @@ class AGIEvalDataset(BaseDataset):
     """
 
     @staticmethod
-    def load(
-        path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs
-    ) -> List[Dict]:
+    def load(path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs) -> List[Dict]:
         dataset = {"test": {}}
 
         files = glob.glob(os.path.join(path, "*.jsonl"))

applications/ColossalEval/colossal_eval/dataset/base.py

@@ -1,7 +1,8 @@
 from abc import abstractstaticmethod
 
-from torch.utils.data import Dataset
 from colossal_eval.utils import jdump
+from torch.utils.data import Dataset
+
 from colossalai.logging import DistributedLogger
 
 
@@ -25,12 +26,13 @@ def save(self, save_path):
     def load(path, logger: DistributedLogger, *args, **kwargs):
         """Load the original dataset and convert it into the inference dataset"""
 
+
 class DistributedDataset(Dataset):
     def __init__(self, data):
         self.data = data
-                
+
     def __len__(self):
         return len(self.data)
-    
+
     def __getitem__(self, idx):
         return self.data[idx]

applications/ColossalEval/colossal_eval/dataset/ceval.py

@@ -90,9 +90,7 @@ class CEvalDataset(BaseDataset):
     """
 
     @staticmethod
-    def load(
-        path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs
-    ) -> List[Dict]:
+    def load(path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs) -> List[Dict]:
         dataset = {"dev": {}, "test": {}}
         for split in ["dev", "test"]:
             files = os.listdir(os.path.join(path, split))

applications/ColossalEval/colossal_eval/dataset/cmmlu.py

@@ -101,9 +101,7 @@ class CMMLUDataset(BaseDataset):
     """
 
     @staticmethod
-    def load(
-        path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs
-    ) -> List[Dict]:
+    def load(path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs) -> List[Dict]:
         dataset = {"dev": {}, "test": {}}
         for split in ["dev", "test"]:
             files = os.listdir(os.path.join(path, split))

applications/ColossalEval/colossal_eval/dataset/gaokaobench.py

@@ -69,9 +69,7 @@ class GaoKaoBenchDataset(BaseDataset):
     """
 
     @staticmethod
-    def load(
-        path: str, logger: DistributedLogger, *args, **kwargs
-    ) -> List[Dict]:
+    def load(path: str, logger: DistributedLogger, *args, **kwargs) -> List[Dict]:
         dataset = {"test": {}}
         for category in ["Fill-in-the-blank_Questions", "Multiple-choice_Questions", "Open-ended_Questions"]:
             files = os.listdir(os.path.join(path, "data", category))

applications/ColossalEval/colossal_eval/dataset/mmlu.py

@@ -31,9 +31,7 @@ class MMLUDataset(BaseDataset):
     """
 
     @staticmethod
-    def load(
-        path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs
-    ) -> List[Dict]:
+    def load(path: str, logger: DistributedLogger, few_shot: bool, *args, **kwargs) -> List[Dict]:
         dataset = {"dev": {}, "test": {}}
         for split in ["dev", "test"]:
             files = os.listdir(os.path.join(path, split))

applications/ColossalEval/colossal_eval/models/huggingface.py

@@ -1,12 +1,11 @@
 import copy
-import math
 from typing import Any, Dict, List, Optional, Tuple
 
 import numpy as np
 import torch
-from torch.utils.data import DataLoader
 from colossal_eval.utils import Conversation, get_batch_prompt, is_rank_0
 from peft import PeftModel
+from torch.utils.data import DataLoader
 from tqdm import tqdm
 from transformers import AutoConfig, AutoModel, AutoModelForCausalLM, AutoTokenizer
 

applications/ColossalEval/colossal_eval/utils/conversation.py

@@ -123,9 +123,7 @@ def dict(self):
         }
 
 
-def get_few_shot_prefix(
-    few_shot_data: List[str], tokenizer: Optional[AutoTokenizer], max_tokens: int
-) -> str:
+def get_few_shot_prefix(few_shot_data: List[str], tokenizer: Optional[AutoTokenizer], max_tokens: int) -> str:
     """
     Get few shot prefix.
 

applications/ColossalEval/examples/dataset_evaluation/inference.py

@@ -4,9 +4,9 @@
 from typing import Dict, List
 
 import torch.distributed as dist
-from torch.utils.data import DataLoader, DistributedSampler
-from colossal_eval.dataset.base import DistributedDataset
 from colossal_eval import dataset, models, utils
+from colossal_eval.dataset.base import DistributedDataset
+from torch.utils.data import DataLoader, DistributedSampler
 
 import colossalai
 from colossalai.accelerator import get_accelerator
@@ -217,11 +217,20 @@ def main(args):
                         dist_dataset = DistributedDataset(category_data["data"])
                     else:
                         dist_dataset = DistributedDataset(prev_questions)
-                        
+
                     sampler = DistributedSampler(dist_dataset, num_replicas=world_size, rank=rank, shuffle=False)
-                    questions_loader = DataLoader(dist_dataset, batch_size=batch_size, sampler=sampler, num_workers=8, pin_memory=True, collate_fn=lambda x: x)
+                    questions_loader = DataLoader(
+                        dist_dataset,
+                        batch_size=batch_size,
+                        sampler=sampler,
+                        num_workers=8,
+                        pin_memory=True,
+                        collate_fn=lambda x: x,
+                    )
                     answers_per_rank = model_.inference(
-                        data_loader=questions_loader, inference_kwargs=category_data["inference_kwargs"], debug=debug_args[dataset_name]
+                        data_loader=questions_loader,
+                        inference_kwargs=category_data["inference_kwargs"],
+                        debug=debug_args[dataset_name],
                     )
                     prev_questions = answers_per_rank
 
@@ -244,7 +253,9 @@ def main(args):
         del model_
         accelerator.empty_cache()
 
-        utils.jdump(dataset_cat_num_mapping, os.path.join(args.inference_save_path, model_name, "dataset_cat_num_mapping.json"))
+        utils.jdump(
+            dataset_cat_num_mapping, os.path.join(args.inference_save_path, model_name, "dataset_cat_num_mapping.json")
+        )
 
     dist.barrier()
     if rank == 0: