llama-factory || AutoDL平台 ||启动web界面

报错如下:

bash 复制代码
root@autodl-container-d83e478b47-3def8c49:~/LLaMA-Factory# llamafactory-cli webui
* Running on local URL:  http://0.0.0.0:7860

Could not create share link. Missing file: /root/miniconda3/lib/python3.10/site-packages/gradio/frpc_linux_amd64_v0.3. 

Please check your internet connection. This can happen if your antivirus software blocks the download of this file. You can install manually by following these steps: 

1. Download this file: https://cdn-media.huggingface.co/frpc-gradio-0.3/frpc_linux_amd64
2. Rename the downloaded file to: frpc_linux_amd64_v0.3
3. Move the file to this location: /root/miniconda3/lib/python3.10/site-packages/gradio

解决办法:

bash 复制代码
cp frpc_linux_amd64_v0.3 /root/miniconda3/lib/python3.10/site-packages/gradio
bash 复制代码
cd /root/miniconda3/lib/python3.10/site-packages/gradio

提高权限

bash 复制代码
 chmod +x frpc_linux_amd64_v0.3

重新执行

bash 复制代码
llamafactory-cli webui
bash 复制代码
 CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat   --model_name_or_path /root/autodl-fs/Qwen2.5-1.5B-Instruct   --template qwen

结果:

bash 复制代码
[INFO|2025-03-02 23:15:05] llamafactory.model.model_utils.attention:157 >> Using torch SDPA for faster training and inference.
[INFO|2025-03-02 23:15:05] llamafactory.model.loader:157 >> all params: 1,543,714,304
* Running on local URL:  http://0.0.0.0:7860
* Running on public URL: https://35d22b023607f1702a.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)

下面的链接就是可访问的动态链接

相关推荐
try2find16 小时前
安装llama-cpp-python踩坑记
开发语言·python·llama
西西弗Sisyphus1 天前
LLaMA-Factory 单卡后训练微调Qwen3完整脚本
微调·llama·llama-factory·后训练
顾道长生'1 天前
(Arxiv-2024)自回归模型优于扩散:Llama用于可扩展的图像生成
计算机视觉·数据挖掘·llama·自回归模型·多模态生成与理解
Zhijun.li@Studio11 天前
【LLaMA-Factory 实战系列】二、WebUI 篇 - Qwen2.5-VL 多模态模型 LoRA 微调保姆级教程
人工智能·自然语言处理·llama·多模态大模型
1213411 天前
LLM:重构数字世界的“智能操作系统”
gpt·aigc·ai编程·llama·gpu算力
冷雨夜中漫步19 天前
Java中如何使用lambda表达式分类groupby
java·开发语言·windows·llama
扫地的小何尚21 天前
全新NVIDIA Llama Nemotron Nano视觉语言模型在OCR基准测试中准确率夺冠
c++·人工智能·语言模型·机器人·ocr·llama·gpu
CFAteam21 天前
DeepSeek AI功能演示:如何生成Verilog脚本
人工智能·ai·fpga开发·llama
Tadas-Gao23 天前
从碳基羊驼到硅基LLaMA:开源大模型家族的生物隐喻与技术进化全景
人工智能·机器学习·大模型·llm·llama
Run_Clover23 天前
llama-factory微调大模型环境配置避坑总结
llama