fix: 为文件读取添加utf-8编码以避免潜在编码问题

docs/chapter5/code/deal_dataset.py

@@ -41,7 +41,7 @@ def convert_message(data):
     return message
 
 with open(output_sft_data, 'a', encoding='utf-8') as sft:
-    with open(sft_data, 'r') as f:
+    with open(sft_data, 'r', encoding='utf-8') as f:
         data = f.readlines()
         for item in tqdm(data, desc="Processing", unit="lines"):
             item = json.loads(item)

docs/chapter5/第五章 动手搭建大模型.md

@@ -1044,7 +1044,7 @@ def convert_message(data):
     return message
 
 with open('BelleGroup_sft.jsonl', 'a', encoding='utf-8') as sft:
-    with open('BelleGroup/train_3.5M_CN.json', 'r') as f:
+    with open('BelleGroup/train_3.5M_CN.json', 'r', encoding='utf-8') as f:
         data = f.readlines()
         for item in tqdm(data, desc="Processing", unit="lines"):
             item = json.loads(item)