Instructions to use BAAI/bge-reranker-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BAAI/bge-reranker-base with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("BAAI/bge-reranker-base") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Inference
- Notebooks
- Google Colab
- Kaggle
do you have a bge-rerank-small version model?
Hey, I am wondering if there is a small reranker model for bge? In addition, I wonder why single-tower model bge-reranker-base is not superior to these two-tower model like stella, etc? That is anazing since as we know two-tower is not performing good in reranking task (in most pairwise tasks.)
Hi, we didn't train a small reranker. You can train your reranker following https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker.
Besides, we didn't train the reranker with much data, so it may not perform well in some scenarios. We suggest to fine-tune it if you want to improve its performance.
Hi, we didn't train a small reranker. You can train your reranker following https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker.
Besides, we didn't train the reranker with much data, so it may not perform well in some scenarios. We suggest to fine-tune it if you want to improve its performance.
I see, thanks!