fix bugs (#2761)

Author: Jintao-Huang

README.md

@@ -147,6 +147,7 @@ CUDA_VISIBLE_DEVICES=0 \
 swift infer \
     --adapters output/vx-xxx/checkpoint-xxx \
     --stream true \
+    --temperature 0 \
     --max_new_tokens 2048
 
 # merge-lora and use vLLM for inference acceleration
@@ -157,6 +158,7 @@ swift infer \
     --merge_lora true \
     --infer_backend vllm \
     --max_model_len 8192 \
+    --temperature 0 \
     --max_new_tokens 2048
 ```
 

README_CN.md

@@ -140,6 +140,7 @@ CUDA_VISIBLE_DEVICES=0 \
 swift infer \
     --adapters output/vx-xxx/checkpoint-xxx \
     --stream true \
+    --temperature 0 \
     --max_new_tokens 2048
 
 # merge-lora并使用vLLM进行推理加速
@@ -150,6 +151,7 @@ swift infer \
     --merge_lora true \
     --infer_backend vllm \
     --max_model_len 8192 \
+    --temperature 0 \
     --max_new_tokens 2048
 ```
 

docs/source/GetStarted/快速开始.md

@@ -64,6 +64,7 @@ CUDA_VISIBLE_DEVICES=0 \
 swift infer \
     --adapters output/vx-xxx/checkpoint-xxx \
     --stream true \
+    --temperature 0 \
     --max_new_tokens 2048
 
 # merge-lora并使用vLLM进行推理加速
@@ -74,6 +75,7 @@ swift infer \
     --merge_lora true \
     --infer_backend vllm \
     --max_model_len 8192 \
+    --temperature 0 \
     --max_new_tokens 2048
 ```
 

docs/source/Instruction/命令行参数.md

@@ -16,10 +16,10 @@
 - custom_register_path: 自定义模型、对话模板和数据集注册的`.py`文件路径
 
 ### 模型参数
-- task_type: 默认为'causal_lm'. 可选为'causal_lm', 'seq_cls'. 例子可以查看[这里](https://github.com/modelscope/ms-swift/tree/main/examples/train/seq_cls).
 - 🔥model: 模型id或模型本地路径。如果是自定义模型请配合`model_type`和`template`使用，具体可以参考[自定义模型](../Customization/自定义模型.md)
 - model_type: 模型类型。相同的模型架构、template、模型加载过程被定义为一个model_type
 - model_revision: 模型版本
+- task_type: 默认为'causal_lm'. 可选为'causal_lm', 'seq_cls'. 例子可以查看[这里](https://github.com/modelscope/ms-swift/tree/main/examples/train/seq_cls).
 - 🔥torch_dtype: 模型权重的数据类型，支持`float16`,`bfloat16`,`float32`，默认从config文件中读取
 - attn_impl: attention类型，支持`flash_attn`, `sdpa`, `eager`，默认使用sdpa
 - num_labels: 分类模型需要指定。代表标签数量，默认为None

docs/source_en/GetStarted/Quick-start.md

@@ -64,6 +64,7 @@ CUDA_VISIBLE_DEVICES=0 \
 swift infer \
     --adapters output/vx-xxx/checkpoint-xxx \
     --stream true \
+    --temperature 0 \
     --max_new_tokens 2048
 
 # merge-lora and use vLLM for inference acceleration
@@ -74,6 +75,7 @@ swift infer \
     --merge_lora true \
     --infer_backend vllm \
     --max_model_len 8192 \
+    --temperature 0 \
     --max_new_tokens 2048
 ```
 

docs/source_en/Instruction/Command-line-parameters.md

@@ -16,11 +16,11 @@ The introduction to command line parameters will cover base arguments, atomic ar
 - custom_register_path: The file path for the custom model, chat template, and dataset registration `.py` files.
 
 ### Model Arguments
-- task_type: Defaults to 'causal_lm'. Options include 'causal_lm' and 'seq_cls'. You can view examples [here](https://github.com/modelscope/ms-swift/tree/main/examples/train/seq_cls).
 - 🔥model: Model ID or local path to the model. If it's a custom model, please use it with `model_type` and `template`. The specific details can be referred to in the [Custom Model](../Customization/Custom-model.md).
 - model_type: Model type. The same model architecture, template, and loading process define a model_type.
 - model_revision: Model version.
 - 🔥torch_dtype: Data type for model weights, supports `float16`, `bfloat16`, `float32`, default is read from the config file.
+- task_type: Defaults to 'causal_lm'. Options include 'causal_lm' and 'seq_cls'. You can view examples [here](https://github.com/modelscope/ms-swift/tree/main/examples/train/seq_cls).
 - attn_impl: Attention type, supports `flash_attn`, `sdpa`, `eager`, default is sdpa.
 - num_labels: To be specified for classification models, representing the number of labels, default is None.
 - rope_scaling: Rope type, supports `linear` and `dynamic`, to be used with `max_length`.

examples/notebook/qwen2.5-self-cognition/infer.sh

@@ -0,0 +1,7 @@
+# Here is the command-line style inference code.
+CUDA_VISIBLE_DEVICES=0 \
+swift infer \
+    --adapters output/vx-xxx/checkpoint-xxx \
+    --stream true \
+    --temperature 0 \
+    --max_new_tokens 2048

examples/notebook/qwen2.5-self-cognition/self-cognition-sft.ipynb

@@ -22,7 +22,7 @@
    "outputs": [],
    "source": [
     "# # install ms-swift\n",
-    "# pip install git+https://github.com/modelscope/ms-swift.git"
+    "# pip install ms-swift -U"
    ]
   },
   {

examples/notebook/qwen2.5-self-cognition/sft.sh

@@ -0,0 +1,30 @@
+# Here is the command-line style training code.
+# 22GB
+CUDA_VISIBLE_DEVICES=0 \
+swift sft \
+    --model Qwen/Qwen2.5-3B-Instruct \
+    --train_type lora \
+    --dataset AI-ModelScope/alpaca-gpt4-data-zh#500 \
+              AI-ModelScope/alpaca-gpt4-data-en#500 \
+              swift/self-cognition#500 \
+    --torch_dtype bfloat16 \
+    --num_train_epochs 1 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --learning_rate 1e-4 \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --target_modules all-linear \
+    --gradient_accumulation_steps 16 \
+    --eval_steps 50 \
+    --save_steps 50 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 2048 \
+    --output_dir output \
+    --system 'You are a helpful assistant.' \
+    --warmup_ratio 0.05 \
+    --dataloader_num_workers 4 \
+    --dataset_num_proc 4 \
+    --model_author 小黄 'Xiao Huang' \
+    --model_name '魔搭' 'ModelScope'

examples/notebook/qwen2vl-ocr/ocr-sft.ipynb

@@ -22,7 +22,7 @@
    "outputs": [],
    "source": [
     "# # install ms-swift\n",
-    "# pip install git+https://github.com/modelscope/ms-swift.git"
+    "# pip install ms-swift -U"
    ]
   },
   {