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")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Alibaba-NLP/UEmbed-2B") model = AutoModelForMultimodalLM.from_pretrained("Alibaba-NLP/UEmbed-2B", device_map="auto")
https://huggingface.co/Alibaba-NLP/UEmbed-2B/resolve/main/vocab.json
hf download hf://Alibaba-NLP/UEmbed-2B/vocab.json
curl -L -o vocab.json https://huggingface.co/Alibaba-NLP/UEmbed-2B/resolve/main/vocab.json
