[docs] update custom_dataset_docs (#4792)

Author: Jintao-Huang

docs/source/Customization/自定义数据集.md

@@ -25,15 +25,21 @@ sharegpt格式:
 {"system": "<system>", "conversation": [{"human": "<query1>", "assistant": "<response1>"}, {"human": "<query2>", "assistant": "<response2>"}]}
 ```
 
-alpaca格式:
+query-response格式:
 ```jsonl
-{"system": "<system>", "instruction": "<query-inst>", "input": "<query-input>", "output": "<response>"}
+{"system": "<system>", "query": "<query2>", "response": "<response2>", "history": [["<query1>", "<response1>"]]}
 ```
+注意：以下字段会自动转成对应的system、query、response字段。
+- system: 'system', 'system_prompt'.
+- query: 'query', 'prompt', 'input', 'instruction', 'question', 'problem'.
+- response: 'response', 'answer', 'output', 'targets', 'target', 'answer_key', 'answers', 'solution', 'text', 'completion', 'content'.
 
-query-response格式：
+alpaca格式:
 ```jsonl
-{"system": "<system>", "query": "<query2>", "response": "<response2>", "history": [["<query1>", "<response1>"]]}
+{"system": "<system>", "instruction": "<query-inst>", "input": "<query-input>", "output": "<response>"}
 ```
+- 注意：instruction和input字段将组合成query字段。若instruction和input不等于空字符串，`query = f'{instruction}\n{input}'`
+
 
 ## 标准数据集格式
 

docs/source_en/Customization/Custom-dataset.md

@@ -26,15 +26,21 @@ ShareGPT format:
 {"system": "<system>", "conversation": [{"human": "<query1>", "assistant": "<response1>"}, {"human": "<query2>", "assistant": "<response2>"}]}
 ```
 
-Alpaca format:
+Query-Response format:
 ```jsonl
-{"system": "<system>", "instruction": "<query-inst>", "input": "<query-input>", "output": "<response>"}
+{"system": "<system>", "query": "<query2>", "response": "<response2>", "history": [["<query1>", "<response1>"]]}
 ```
+Note: The following fields will be automatically converted to the corresponding system, query, and response fields.
+- system: 'system', 'system_prompt'.
+- query: 'query', 'prompt', 'input', 'instruction', 'question', 'problem'.
+- response: 'response', 'answer', 'output', 'targets', 'target', 'answer_key', 'answers', 'solution', 'text', 'completion', 'content'.
 
-Query-Response format:
+Alpaca format:
 ```jsonl
-{"system": "<system>", "query": "<query2>", "response": "<response2>", "history": [["<query1>", "<response1>"]]}
+{"system": "<system>", "instruction": "<query-inst>", "input": "<query-input>", "output": "<response>"}
 ```
+- Note: The instruction and input fields will be combined into the query field. If instruction and input are not empty strings, then `query = f'{instruction}\n{input}'`.
+
 
 ## Standard Dataset Format