Spaces:
Running
on
T4
Apply for community grant: Academic project
Hi, we have built a multi-modal chatGPT-like model named mPLUG-Owl. It is a novel model that equips LLMs with multi-modal abilities through modularized learning of foundation LLM, a visual knowledge module, and a visual abstractor module. This approach can support multiple modalities and facilitate diverse unimodal and multimodal abilities through modality collaboration. Experimental results show that our model outperforms existing
multi-modal models (such as MiniGPT-4), demonstrating mPLUG-Owl’s impressive instruction and visual understanding ability, multi-turn conversation ability, and knowledge reasoning ability. Besides, we observe some unexpected and exciting abilities such as multi-image correlation and scene text understanding, which makes it possible to leverage it for harder real scenarios, such as vision-only document comprehension.
We also provide the github code for it: https://github.com/X-PLUG/mPLUG-Owl
As well as hosting a demo on modelscope: https://modelscope.cn/studios/damo/mPLUG-Owl/summary
Therefore, we are happy to host the demo on huggingface as well. However, due to the money shortage, we cannot afford the demo with GPU. Our demo requires a GPU with 24Gb or larger memory. We would provide the latest multi-lingustic model on Huggingface ONLY. Hope you can consider it. Thanks.
Hi @MAGAer13 , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus