Feature Extraction
Transformers
Safetensors
qwen3_5
image-text-to-text
embeddings
multimodal
retrieval
sparse-retrieval
splade
dense-retrieval
vision
Instructions to use Alibaba-NLP/UEmbed-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-NLP/UEmbed-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Alibaba-NLP/UEmbed-9B")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Alibaba-NLP/UEmbed-9B") model = AutoModelForMultimodalLM.from_pretrained("Alibaba-NLP/UEmbed-9B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- examples
- src
- 1.57 kB
- 11.3 kB
- 6.14 kB
- 7.76 kB
- 3.13 kB
- 51 Bytes
- 3.35 MB
- 2.03 GB xet
- 975 MB xet
- 990 MB xet
- 974 MB xet
- 958 MB xet
- 974 MB xet
- 991 MB xet
- 982 MB xet
- 950 MB xet
- 990 MB xet
- 974 MB xet
- 957 MB xet
- 974 MB xet
- 991 MB xet
- 940 MB xet
- 991 MB xet
- 139 MB xet
- 64.6 kB
- 390 Bytes
- 1.19 kB
- 5.75 MB
- 1.51 GB xet
- 20 MB xet
- 16.7 kB
- 385 Bytes
- 6.72 MB