Roberyan

Token indices sequence length is longer than the specified maximum sequence length for this model (565 > 512). Running this sequence through the model will result in indexing errors

1

I am trying to retrain the LISA with 7B model, I encounter such warning: Token indices sequence length is longer than the specified maximum sequence length for this model (565...

Errors when installing the package

8

pip install mamba-ssm Collecting mamba-ssm Downloading mamba_ssm-1.2.0.post1.tar.gz (34 kB) Preparing metadata (setup.py) ... error error: subprocess-exited-with-error × python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [13...

Hi, may I know is your training dataset available for download? Does your dataset have segmentation label with mentioned image and text as input?

When running the offline demo as instruction markdown, I find that the code can not always work. It may work for some sample, and would appear such error: ``` Traceback...

Fail to install webots on WSL2 Ubuntu-22.04

3

**Describe the Bug** Though appointing `WEBOTS_HOME`,`ros2 launch webots_ros2_universal_robot multirobot_launch.py` cmd always says "Do you want Webots R2023b to be automatically installed in C:\Program Files\Webots ([Y]es/[N]o)?" And this will fails with...

Hi, I want to know if the image feature and multi modal feature has position meaning to the original image? Like the blip2_feature_extractor produce (1,32,768) for both image feature and...

 I am using blip2's feature extraction, however for the `feature_text`, the text_embedding shape is [1,6,768] instead of [1,12,768], I am confused if this is the case or I did...

I want to use BLIP-2 in downstream tasks which only supporting numpy version==1.23, however blip2 in lavis needs numpy version>=2.0, I wonder if there is anyway to extract the blip-2...