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 SentenceTransformer model = SentenceTransformer("BAAI/bge-reranker-base") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - 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!