Aliayub1995
/

VideoLLaMA2-7B

Visual Question Answering

videollama2_mistral

text-generation

multimodal large language model

large video-language model

Inference Endpoints

Model card Files Files and versions Community

Aliayub1995 commited on Sep 4

Commit

c046ba1

•

1 Parent(s): 89a6901

Update videollama2/init.py

Files changed (1) hide show

videollama2/__init__.py +1 -1

videollama2/__init__.py CHANGED Viewed

@@ -33,7 +33,7 @@ def model_init(model_path=None, **kwargs):
     return model, processor, tokenizer
-def mm_infer(url, instruct, model, tokenizer, modal='video', **kwargs):
     """inference api of VideoLLaMA2 for video understanding.
     Args:

     return model, processor, tokenizer
+def mm_infer(image_or_video, instruct, model, tokenizer, modal='video', **kwargs):
     """inference api of VideoLLaMA2 for video understanding.
     Args: