zhangxyzte

Results 2 comments of zhangxyzte

> > Maybe you have built the original vary? Please rebuild the vary-toy. > > 在WSL2里跑的,碰到了同样的问题,看文档里没有build的说明,且步骤中与原版vary无明显区分(比如`cd /path/to/vary`而不是`cd /path/to/Vary-toy`)。 修改了代码中的路径重新`pip install e .`(这步是不是build?) 仍出现: > > ``` > You should probably...

> 能发一下都改了哪里吗,我下载了 Vary-toy weights,放到了/data/toy_weights下面,然后把vary_toy_qwen1_8.py里面的模型路径改成了这个,执行这个命令:python vary/demo/run_qwen_vary.py --model-name /data/toy_weights/ --image-file 3.png,会报你截图的那个错,我把run_qwen_vary.py里面的image_processor = CLIPImageProcessor.from_pretrained("/data/hypertext/ucaswei/cache/vit-large-patch14/vit-large-patch14/", torch_dtype=torch.float16)这个路径改成/data/toy_weights/或者/cache/vit-large-patch14/都不行,/cache/vit-large-patch14/里面有之前配置vary时下载的模型 vary_toy_qwen1_8.py这个路径最后我没改,把vit-large-patch14权重放到原始/data/hypertext/ucaswei/cache/vit-large-patch14/vit-large-patch14/下,或者重配python环境再试试