Update README.md

README.md

@@ -82,20 +82,13 @@ pip install e . -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirro
 ## 训练
 
 使用LLaMA-Factory框架微调
-### 模型下载
 
-[qwen2-7B模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-7B)
-
-[qwen2-7B-Instruct模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-7B-Instruct)
-
-[qwen2-72B模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-72B)
-
-[qwen2-72B-Instruct模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-72B-Instruct)
 ### 单机单卡（LoRA-finetune）
 ```
 #注意：根据自己的模型切换.yaml文件中的模型位置并调整其他参数
 cd /path/your_code_data/
 cd LLaMA-Factory
+export FORCE_TORCHRUN=1
 HIP_VISIBLE_DEVICES=0 llamafactory-cli train examples/train_lora/qwen2_lora_sft_ds3.yaml
 ```
 
@@ -149,8 +142,19 @@ python ./inference_vllm/Qwen2_72B_inference.py
 `对话问答`
 ### 热点应用行业
 `科研,教育,政府,金融`
+
+## 预训练权重
+
+[qwen2-7B模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-7B)
+
+[qwen2-7B-Instruct模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-7B-Instruct)
+
+[qwen2-72B模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-72B)
+
+[qwen2-72B-Instruct模型下载SCNet链接](http://113.200.138.88:18080/aimodels/Qwen2-72B-Instruct)
+
 ## 源码仓库及问题反馈
-- http://developer.hpccube.com/codes/modelzoo/qwen1.5-pytorch.git
+- https://developer.hpccube.com/codes/modelzoo/qwen2_pytorch
 ## 参考资料
 - https://github.com/hiyouga/LLaMA-Factory
 - https://github.com/QwenLM/Qwen2