Feature Extraction
Transformers
Safetensors
qwen3_5
embeddings
multimodal
retrieval
sparse-retrieval
splade
dense-retrieval
vision
Instructions to use Alibaba-NLP/UEmbed-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-NLP/UEmbed-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Alibaba-NLP/UEmbed-4B")# Load model directly from transformers import AutoProcessor, Qwen3_5ForEmbedding processor = AutoProcessor.from_pretrained("Alibaba-NLP/UEmbed-4B") model = Qwen3_5ForEmbedding.from_pretrained("Alibaba-NLP/UEmbed-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4b5ca43f58daaa476d06507929400a719fa0d2f25d331745aee75c5574b8c61c
- Size of remote file:
- 943 MB
- SHA256:
- 8d314442559be2d43594b750df64808416d2313daa6874ee6c35463380d3eb6b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.