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")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Alibaba-NLP/UEmbed-4B") model = AutoModelForMultimodalLM.from_pretrained("Alibaba-NLP/UEmbed-4B", device_map="auto")
https://huggingface.co/Alibaba-NLP/UEmbed-4B/resolve/main/sparse_info.json
hf download hf://Alibaba-NLP/UEmbed-4B/sparse_info.json
curl -L -o sparse_info.json https://huggingface.co/Alibaba-NLP/UEmbed-4B/resolve/main/sparse_info.json
