lint

Author: neginraoof

eval/chat_benchmarks/HumanEval/eval_instruct.py

@@ -112,7 +112,9 @@ def generate_responses(self, model: LM) -> Dict[str, Any]:
                 self.logger.info("Generating responses for Human Eval...")
                 outputs = self.compute(model, all_instances)
 
-                is_main_process = model.accelerator.process_index == 0 if hasattr(model, 'accelerator') else model.world_size <= 1
+                is_main_process = (
+                    model.accelerator.process_index == 0 if hasattr(model, "accelerator") else model.world_size <= 1
+                )
                 if not is_main_process:
                     continue
 

eval/chat_benchmarks/IFEval/eval_instruct.py

@@ -115,7 +115,9 @@ def generate_responses(self, model: LM) -> Dict[str, Any]:
             self.logger.info("Generating responses...")
             outputs = self.compute(model, all_instances)
 
-            is_main_process = model.accelerator.process_index == 0 if hasattr(model, 'accelerator') else model.world_size <= 1
+            is_main_process = (
+                model.accelerator.process_index == 0 if hasattr(model, "accelerator") else model.world_size <= 1
+            )
             if not is_main_process:
                 return None
 

eval/chat_benchmarks/MBPP/eval_instruct.py

@@ -161,7 +161,9 @@ def generate_responses(self, model: LM) -> Dict[str, Any]:
             outputs = self.compute(model, all_instances)
 
             # Return None early for non-primary ranks
-            is_main_process = model.accelerator.process_index == 0 if hasattr(model, 'accelerator') else model.world_size <= 1
+            is_main_process = (
+                model.accelerator.process_index == 0 if hasattr(model, "accelerator") else model.world_size <= 1
+            )
             if not is_main_process:
                 return None
 

eval/chat_benchmarks/MTBench/eval_instruct.py

@@ -151,7 +151,9 @@ def get_model_answers(self, model: LM, model_id: str, questions: List[Dict[str,
                     all_convs[q_idx].append({"role": "assistant", "content": output})
                     all_choices[q_idx]["turns"].append(output)
 
-            is_main_process = model.accelerator.process_index == 0 if hasattr(model, 'accelerator') else model.world_size <= 1
+            is_main_process = (
+                model.accelerator.process_index == 0 if hasattr(model, "accelerator") else model.world_size <= 1
+            )
             if not is_main_process:
                 continue
 

eval/chat_benchmarks/MTBench/fastchat/data/clean_sharegpt.py

@@ -5,6 +5,7 @@
 Usage:
 python3 -m fastchat.data.clean_sharegpt --in sharegpt_html.json --out sharegpt_clean.json
 """
+
 import argparse
 from concurrent.futures import ProcessPoolExecutor
 import json
@@ -19,9 +20,7 @@
 
 div_pattern = re.compile("<div.*?>")
 span_pattern = re.compile("<span.*?>")
-code_lang_pattern = re.compile(
-    "```\s*" + "(.*?)" + "(?:Copy code)+" + "(.+?)" + "\s*?```", re.DOTALL
-)
+code_lang_pattern = re.compile("```\s*" + "(.*?)" + "(?:Copy code)+" + "(.+?)" + "\s*?```", re.DOTALL)
 code_lang_format = "```\g<1>\n\g<2>\n```"
 regenerate_pattern = re.compile("\d+ / \d+")
 copy_chars_pattern = re.compile("Copy\d+ chars / \d+ words")
@@ -155,9 +154,7 @@ def clean_html_all(content, begin, end):
     content = content[begin:end]
     processed = []
     with ProcessPoolExecutor() as executor:
-        for result in tqdm(
-            executor.map(clean_html_one_sample, content), total=len(content)
-        ):
+        for result in tqdm(executor.map(clean_html_one_sample, content), total=len(content)):
             processed.append(result)
 
     visited = {}

eval/chat_benchmarks/MTBench/fastchat/data/extract_gpt4_only.py

@@ -3,6 +3,7 @@
 
 Usage: python3 -m fastchat.data.extract_gpt4_only --in sharegpt.json
 """
+
 import argparse
 import json
 

eval/chat_benchmarks/MTBench/fastchat/data/extract_single_round.py

@@ -3,6 +3,7 @@
 
 Usage: python3 -m fastchat.data.extract_single_round --in sharegpt.json
 """
+
 import argparse
 import json
 

eval/chat_benchmarks/MTBench/fastchat/data/filter_wrong_format.py

@@ -5,6 +5,7 @@
 python3 -m fastchat.data.filter_wrong_format --in input.json --out output.json
 
 """
+
 import argparse
 import json
 import re

eval/chat_benchmarks/MTBench/fastchat/data/get_stats.py

@@ -26,9 +26,7 @@ def tokenize_one_sample(c):
 def tokenize_dataset(content):
     processed = []
     with ProcessPoolExecutor() as executor:
-        for result in tqdm(
-            executor.map(tokenize_one_sample, content), total=len(content)
-        ):
+        for result in tqdm(executor.map(tokenize_one_sample, content), total=len(content)):
             processed.append(result)
 
     return processed
@@ -59,9 +57,7 @@ def compute_stats(content):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--in-file", type=str)
-    parser.add_argument(
-        "--model-name-or-path", type=str, default="meta-llama/Llama-2-7b-chat-hf"
-    )
+    parser.add_argument("--model-name-or-path", type=str, default="meta-llama/Llama-2-7b-chat-hf")
     args = parser.parse_args()
 
     content = json.load(open(args.in_file, "r"))

eval/chat_benchmarks/MTBench/fastchat/data/hardcoded_questions.py

@@ -1,6 +1,7 @@
 """
 Hardcoded question and answers.
 """
+
 import json