GetDavid
GetDavid
> May I know the contents of the local model path? sure，is`/home/zdw/Open-Sora/pre_training/llava-v1.6-34b` I waited for a long time, but when the download was completed, it worked normally. What was it...
> 有重新再install一遍吗？ 重新安装什么？
> Creat one and reinstall it Reinstall what, the conda environment, or what?
> > > Creat one and reinstall it > > > > > > Reinstall what, the conda environment, or what? > > only opensora I tried the following command...
> https://github.com/hpcaitech/Open-Sora/blob/a37a189482a4cd1c7892aa06881e539cbf8078ce/configs/opensora/inference/16x256x256.py#L19-L23 > > > 改成 > ``` > text_encoder = dict( > type="t5", > from_pretrained="path/to/your/model", > model_max_length=120, > local_cache=True, > ) > ``` > > 注意，如果你的模型下载路径为, 在这里应该传入：`/home/xxx/model/t5-v1_1-xxl``from_pretrained="/home/xxx/model"` 我遇到了同样的问题，但是我下载好以后路径变为 `(base)...
> > > https://github.com/hpcaitech/Open-Sora/blob/a37a189482a4cd1c7892aa06881e539cbf8078ce/configs/opensora/inference/16x256x256.py#L19-L23 > > > > > > 改成 > > > ``` > > > text_encoder = dict( > > > type="t5", > > > from_pretrained="path/to/your/model", >...
> > > > https://github.com/hpcaitech/Open-Sora/blob/a37a189482a4cd1c7892aa06881e539cbf8078ce/configs/opensora/inference/16x256x256.py#L19-L23 > > > > > > > > 改成 > > > > ``` > > > > text_encoder = dict( > > > >...
> Now we have added automatic downloading. You do not need to download by yourself. 自动下载的话是保存到什么路径？哪里使用了这个路径呢？
> 检查是不是安装好cuda toolkit,使用nvcc命令，如果command not found就没安装（我安装好了之后nvcc仍然不能使用，指定环境变量就好了），然后再安装flash-attn应该就好了 你好，我可以使用nvidia-smi，且可以正常推理。但是我无法安装flash-attn，一直在setup.py的环节，长达1小时，依旧没有构建好，你知道一些可能的原因吗？