fix sft system (#2262)

modelscope · Oct 16, 2024 · 82e2522 · 82e2522
1 parent fb97bba
commit 82e2522
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -656,7 +656,7 @@ The complete list of supported models and datasets can be found at [Supported Mo
 
 ### Supported Open Source Datasets
 
-| Dataset Type        | Training Task   | Documentation                                                                                                                                                                                                                                |
+| Dataset Type        | Training Task   | Dataset                                                                                                                                                                                                                                |
 |---------------------|:----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | General             | Fine-tuning     | 🔥ruozhiba, 🔥ms-bench, 🔥alpaca-en(gpt4), 🔥alpaca-zh(gpt4), multi-alpaca, instinwild, cot-en, cot-zh, firefly-zh, instruct-en, gpt4all-en, sharegpt, tulu-v2-sft-mixture, wikipedia-zh, open-orca, sharegpt-gpt4, deepctrl-sft, coig-cqia. |
 | Agent               | Fine-tuning     | 🔥ms-agent, 🔥ms-agent-for-agentfabric, ms-agent-multirole, 🔥toolbench-for-alpha-umi, damo-agent-zh, damo-agent-zh-mini, agent-instruct-all-en.                                                                                             |

diff --git a/README_CN.md b/README_CN.md
@@ -650,7 +650,7 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
 
 ### 支持的开源数据集
 
-| 数据集类型 | 训练任务 | 文档                                                                                                                                                                                                                                           |
+| 数据集类型 | 训练任务 | 数据集                                                                                                                                                                                                                                          |
 |-------|:-----|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | 通用    | 微调   | 🔥ruozhiba, 🔥ms-bench, 🔥alpaca-en(gpt4), 🔥alpaca-zh(gpt4), multi-alpaca, instinwild, cot-en, cot-zh, firefly-zh, instruct-en, gpt4all-en, sharegpt, tulu-v2-sft-mixture, wikipedia-zh, open-orca, sharegpt-gpt4, deepctrl-sft, coig-cqia. |
 | Agent | 微调   | 🔥ms-agent, 🔥ms-agent-for-agentfabric, ms-agent-multirole, 🔥toolbench-for-alpha-umi, damo-agent-zh, damo-agent-zh-mini, agent-instruct-all-en.                                                                                             |

diff --git a/swift/llm/sft.py b/swift/llm/sft.py
@@ -320,8 +320,7 @@ def prepare_model_template_train(args, msg: Optional[Dict[str, Any]] = None):
     template._is_training = True
     if args.streaming:
         template.encode = partial(template.encode, streaming=args.streaming)
-    args.system = template.default_system
-    logger.info(f'system: {args.system}')
+    logger.info(f'system: {template.default_system}')
     logger.info(f'args.lazy_tokenize: {args.lazy_tokenize}')
 
     if not isinstance(args, RLHFArguments):