From 5058900e53609b0c7f8dc58ae10d9a03f2ef9f2b Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 27 Jul 2026 16:30:36 +0000
Subject: [PATCH 1/2] [pre-commit.ci] pre-commit autoupdate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

updates:
- [github.com/pre-commit/pre-commit-hooks: v5.0.0 → v6.0.0](https://github.com/pre-commit/pre-commit-hooks/compare/v5.0.0...v6.0.0)
- [github.com/astral-sh/ruff-pre-commit: v0.11.0 → v0.16.0](https://github.com/astral-sh/ruff-pre-commit/compare/v0.11.0...v0.16.0)
---
 .pre-commit-config.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index b4f4000..11bdd97 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,12 +1,12 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.0
+    rev: v0.16.0
     hooks:
       - id: ruff
         args: [--fix]

From 90e5732bf8d28a1545a438cf764bc4b71d6c4d70 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 27 Jul 2026 16:30:50 +0000
Subject: [PATCH 2/2] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 data/test_data_loading.py |  3 ++-
 dataset.py                | 11 ++++++-----
 demo.py                   |  5 +++--
 full_automation.py        |  5 ++---
 utils/tool_utils.py       |  6 +++---
 5 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/data/test_data_loading.py b/data/test_data_loading.py
index ad481da..6749762 100644
--- a/data/test_data_loading.py
+++ b/data/test_data_loading.py
@@ -1,6 +1,7 @@
-import pytest
 import json
 
+import pytest
+
 
 @pytest.fixture
 def load_data():
diff --git a/dataset.py b/dataset.py
index c717595..675204e 100644
--- a/dataset.py
+++ b/dataset.py
@@ -1,9 +1,10 @@
 import json
-from typing import Any, Dict, List
+from typing import Any
 
 import torch
 from loguru import logger
 from torch.utils.data import Dataset
+
 from utils.tool_utils import function_formatter
 
 
@@ -18,10 +19,10 @@ def __init__(self, file, tokenizer, max_seq_length, template):
         self.observation_format = template["observation_format"]
 
         self.max_seq_length = max_seq_length
-        logger.info("Loading data: {}".format(file))
+        logger.info(f"Loading data: {file}")
         with open(file, "r", encoding="utf8") as f:
             data_list = f.readlines()
-        logger.info("There are {} data in dataset".format(len(data_list)))
+        logger.info(f"There are {len(data_list)} data in dataset")
         self.data_list = data_list
 
     def __len__(self):
@@ -93,13 +94,13 @@ def __getitem__(self, index):
         return inputs
 
 
-class SFTDataCollator(object):
+class SFTDataCollator:
     def __init__(self, tokenizer, max_seq_length):
         self.tokenizer = tokenizer
         self.max_seq_length = max_seq_length
         self.pad_token_id = tokenizer.pad_token_id
 
-    def __call__(self, batch: List[Dict[str, Any]]) -> Dict[str, Any]:
+    def __call__(self, batch: list[dict[str, Any]]) -> dict[str, Any]:
         # Find the maximum length in the batch
         lengths = [len(x["input_ids"]) for x in batch if x["input_ids"] is not None]
         # Take the maximum length in the batch, if it exceeds max_seq_length, take max_seq_length
diff --git a/demo.py b/demo.py
index 1c6ee73..6187472 100644
--- a/demo.py
+++ b/demo.py
@@ -2,10 +2,11 @@
 from dataclasses import dataclass
 
 import torch
+from datasets import Dataset
 from peft import LoraConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-from trl import SFTTrainer, SFTConfig
-from datasets import Dataset
+from trl import SFTConfig, SFTTrainer
+
 from dataset import SFTDataCollator, SFTDataset
 from utils.constants import model2template
 
diff --git a/full_automation.py b/full_automation.py
index d1efd5e..5dfdde6 100644
--- a/full_automation.py
+++ b/full_automation.py
@@ -3,8 +3,8 @@
 
 import requests
 import yaml
-from loguru import logger
 from huggingface_hub import HfApi
+from loguru import logger
 
 from demo import LoraTrainingArguments, train_lora
 from utils.constants import model2base_model, model2size
@@ -36,8 +36,7 @@
     # download in chunks
     response = requests.get(data_url, stream=True)
     with open("data/demo_data.jsonl", "wb") as f:
-        for chunk in response.iter_content(chunk_size=8192):
-            f.write(chunk)
+        f.writelines(response.iter_content(chunk_size=8192))
 
     # train all feasible models and merge
     for model_id in all_training_args.keys():
diff --git a/utils/tool_utils.py b/utils/tool_utils.py
index 2aa2934..90da8d0 100644
--- a/utils/tool_utils.py
+++ b/utils/tool_utils.py
@@ -1,5 +1,5 @@
-from typing import Dict, Any, List, Tuple
 import json
+from typing import Any
 
 DEFAULT_TOOL_PROMPT = (
     "You have access to the following tools:\n{tool_text}"
@@ -14,7 +14,7 @@
 DEFAULT_FUNCTION_SLOTS = "Action: {name}\nAction Input: {arguments}\n"
 
 
-def tool_formater(tools: List[Dict[str, Any]]) -> str:
+def tool_formater(tools: list[dict[str, Any]]) -> str:
     tool_text = ""
     tool_names = []
     for tool in tools:
@@ -52,7 +52,7 @@ def tool_formater(tools: List[Dict[str, Any]]) -> str:
 
 
 def function_formatter(tool_calls, function_slots=DEFAULT_FUNCTION_SLOTS) -> str:
-    functions: List[Tuple[str, str]] = []
+    functions: list[tuple[str, str]] = []
     if not isinstance(tool_calls, list):
         tool_calls = [tool_calls]  # parrallel function calls