DAMO-NLP-SG
/

VideoLLaMA2.1-7B-AV

Visual Question Answering

videollama2_qwen2

text-generation

Audio-visual Question Answering

Audio Question Answering

multimodal large language model

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (0)

Some weights of Videollama2Qwen2ForCausalLM were not initialized from the model checkpoint at ./VideoLLaMA2.1-7B-AV and are newly initialized:

#4 opened 6 days ago by

Does this model support 'image' inference?

#3 opened about 2 months ago by

can you please tell me if the paths in config.json here needs to be modified when I run AV branch?

#2 opened about 2 months ago by

'process_video() got an unexpected keyword argument 'va'‘

#1 opened about 2 months ago by