Liuhui Wang

I wonder if you get 'nan' when using position embedding. Thanks.

A bug shows when the batch_size sets 1

1

When I set batch_size 1, a bug shows as "ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1, 1])". I wonder how to...

A question about the version of pytorch

1

Can this code support higher versions of pytorch? I was unable to successfully configure the required pytorch environment.

Pre-trained models for segmentation

1

I would like to ask if you could provide pre-trained models for segmentation?

CUDA error: unknown error

3

When I finetuned the G-LLava on 8 A100s, I met such a problem several times. The full trace is here https://drive.google.com/file/d/195PO96uWKnx4LE3BWjxm0DsrQxWbj3QP/view?usp=sharing The script is here https://github.com/pipilurj/G-LLaVA/blob/main/scripts It worked well for...

### Question When I finetuned the llava, I met such a problem "Unable to determine the device handle for GPU0000:4F:00.0: Unknown Error". I finetuned on eight A100 gpu. This problem...

When will the code be released?

1

Hi, thanks for your wonderful work. I wonder when will the code be released?