How to use thu-nmrc/bge-small-structural-separator with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="thu-nmrc/bge-small-structural-separator")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("thu-nmrc/bge-small-structural-separator") model = AutoModel.from_pretrained("thu-nmrc/bge-small-structural-separator", device_map="auto")
https://huggingface.co/thu-nmrc/bge-small-structural-separator/resolve/main/tokenizer.json
hf download hf://thu-nmrc/bge-small-structural-separator/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/thu-nmrc/bge-small-structural-separator/resolve/main/tokenizer.json
