Visual Question Answering
Transformers
Safetensors
English
videollama3_qwen2
text-generation
multi-modal
large-language-model
video-language-model
custom_code
Instructions to use DAMO-NLP-SG/VideoLLaMA3-7B-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA3-7B-Image with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="DAMO-NLP-SG/VideoLLaMA3-7B-Image", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA3-7B-Image", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
find a bug in load_images func
#3
by menglan - opened
in load_images func, this line code will go wrong:
elif isinstance(image_path, str) and image_path.startswith("http://") or image_path.startswith("https://"):
it should be
elif isinstance(image_path, str) and (image_path.startswith("http://") or image_path.startswith("https://")):
and it is different from https://github.com/DAMO-NLP-SG/VideoLLaMA3/blob/main/inference/transformers_api/processing_videollama3.py#L294