Feature Extraction
Transformers
Safetensors
qwen3_5
embeddings
multimodal
retrieval
sparse-retrieval
splade
dense-retrieval
vision
Instructions to use Alibaba-NLP/UEmbed-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-NLP/UEmbed-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Alibaba-NLP/UEmbed-2B")# Load model directly from transformers import AutoProcessor, Qwen3_5ForEmbedding processor = AutoProcessor.from_pretrained("Alibaba-NLP/UEmbed-2B") model = Qwen3_5ForEmbedding.from_pretrained("Alibaba-NLP/UEmbed-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c2d239ab16a145def217d3cb43bee30180570fc5960989f5e1012e7c1b9a3f20
- Size of remote file:
- 754 MB
- SHA256:
- bb55b3e2068b6551c76211e05e32802400002d22cb580e24410a2d819eb69da1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.