Alibaba-DAMO-Academy
/

PixelRefer-2B

Video-Text-to-Text

pixelrefer_qwen2

text-generation

multimodal large language model

large video-language model

Model card Files Files and versions

8.8 GB

1 contributor

History: 5 commits

SFconvertbot's picture

Adding `safetensors` variant of this model

1c1de36 verified 2 months ago