luckytalk
luckytalk
> ### Is there an existing issue for this? > * [x] I have searched the existing issues > > ### Current Behavior > 目前提供的docker镜像是使用GPU的版本，如何在DOCKER中布署CPU版本？ > > ### Expected Behavior...
解决了，是内存不够。运行INT4就没问题
能不能给个cli的例子？
ValueError: The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder` for them. Alternatively, make sure you have `safetensors` installed if the model you are using offers...
Why can't I use a 20 node cluster to run projects instead of using a GPU?
项目运行起来后，生成测试视频错误，报错torch，可能是PyTorch 和 torchvision 的版本不兼容 RuntimeError: Couldn't load custom C++ ops. This can happen if your PyTorch and torchvision versions are incompatible, or if you had errors while compiling torchvision from...
谢谢，拜托 在 2024-05-31 09:58:06，"LeoWood" ***@***.***> 写道： 您的邮件已收到，我将尽快回复，谢谢。刘欢 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***>
PyTorch 和 torchvision 的版本不兼容的问题已解决。安装与torch匹配的torchvision即可（0.18.0）
现在遇到新的问题，在页面上使用tts合成语音时报错： 'TTS' object has no attribute 'speakers'
PyTorch 和 torchvision 的版本不兼容的问题已解决。安装与torch匹配的torchvision即可（0.18.0） 现在遇到新的问题，在页面上使用tts合成语音时报错： 'TTS' object has no attribute 'speakers' 在 2024-05-31 09:58:06，"LeoWood" ***@***.***> 写道： 您的邮件已收到，我将尽快回复，谢谢。刘欢 — Reply to this email directly, view it on GitHub, or unsubscribe. You...