武文骥 comments

Results 5 comments of


                                            武文骥

trafficstars

uranker 的结果出现负值

> 指标并没有做归一化，不用care正负，比较大小就可以作者您好，请问就是比较他们的绝对值是吗

model type `multi_modality` but Transformers does not recognize this architecture

同问

> 嗨，由于网络限制，我正在尝试从本地路径加载 ViT-SO400M-14-SigLIP-384 权重。我修改了配置以替换为，但它抛出 .如何在不更改版本的情况下从本地目录正确加载权重？`siglip/CLIP-ViT-SO400M-14-384``/home/xxx/data/model_hub/ViT-SO400M-14-SigLIP-384``ValueError: Unknown vision tower: during loading``transformers==4.51.3` Same question，my H100 can not connect to the Internet, I try to use the download model but I don't...

RuntimeError: Expected tensor for argument #1 'input' to have the same type as tensor for argument #2 'weight'; but type torch.cuda.FloatTensor does not equal torch.cuda.HalfTensor (while checking arguments for cudnn_batch_norm)

你后面那个像是显存崩了，关了重新进试试？

ValueError: The checkpoint you are trying to load has model type `multi_modality` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

同问

武文骥

uranker 的结果出现负值

model type `multi_modality` but Transformers does not recognize this architecture

How to load checkpoints?

RuntimeError: Expected tensor for argument #1 'input' to have the same type as tensor for argument #2 'weight'; but type torch.cuda.FloatTensor does not equal torch.cuda.HalfTensor (while checking arguments for cudnn_batch_norm)

ValueError: The checkpoint you are trying to load has model type `multi_modality` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.