# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("OpenMatch/Web-Graph-Embedding")
model = AutoModel.from_pretrained("OpenMatch/Web-Graph-Embedding")Quick Links
The Embedding Model in Paper: Distributionally Robust Unsupervised Dense Retrieval Training on Web Graphs.
This model is trained by predicting links between web pages. It serves as an encoder to generate dense vectors that are later used for clustering documents. If you want to reproduce our evaluation results or learn more about our work, please refer to https://github.com/OpenMatch/Web-DRO .
- Downloads last month
- 19
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="OpenMatch/Web-Graph-Embedding")