Feature Extraction
Transformers
PyTorch
qwen3_vl
embeddings
multimodal
retrieval
compositional-reasoning
vision
reranker-distillation
Instructions to use Alibaba-NLP/core-emb-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-NLP/core-emb-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Alibaba-NLP/core-emb-2b")# Load model directly from transformers import AutoProcessor, Qwen3VLForEmbedding processor = AutoProcessor.from_pretrained("Alibaba-NLP/core-emb-2b") model = Qwen3VLForEmbedding.from_pretrained("Alibaba-NLP/core-emb-2b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Alibaba-NLP/core-emb-2b: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/Alibaba-NLP/core-emb-2b/resolve/main/tokenizer.json
- Command line
-
hf download hf://Alibaba-NLP/core-emb-2b/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Alibaba-NLP/core-emb-2b/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 7f7828f2f177a8fecc364286be9c2c09ea5c1890f3c6f6b4c0ef6aa5f57d44c5
- Size of remote file:
- 11.4 MB
- SHA256:
- def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.