Sentence Similarity
Transformers
Safetensors
PyTorch
English
qwen2_5_vl
feature-extraction
video
retrieval
embedding
multimodal
qwen2.5-vl
custom_code
Instructions to use Alibaba-NLP/GVE-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-NLP/GVE-3B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("Alibaba-NLP/GVE-3B", trust_remote_code=True) model = AutoModel.from_pretrained("Alibaba-NLP/GVE-3B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Could you please provide a example of the full retrieval pipeline?
#4
by AaronWho - opened
Could you please provide a complete retrieval case example? For instance, the full workflow for inputting a video, a query command, and calculating the similarity.
Thanks for your interest! We are sorry that we have not well prepared our full retrieval pipeline code. But using our example codes, you can output embeddings in a torch.Tensor or np.Array type, which is compatible with most popular retrieval frameworks. Try to use our model and embedding process as a plug-in module in a general retrieval pipeline.