GeoGPT-Research-Project commited on
Commit
db5c62e
·
verified ·
1 Parent(s): 84665c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -1,3 +1,9 @@
 
 
 
 
 
 
1
  # GeoReranker
2
 
3
  The GeoReranker model is a critical component in Retrieval-Augmented Generation (RAG) systems, designed to refine the initial retrieval results by reordering candidate documents based on their semantic relevance to the query. Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
@@ -29,4 +35,4 @@ The model is not intended for use in any manner that violates applicable laws or
29
 
30
 
31
  ## Limitations
32
- GeoReranker is trained on English datasets, and performance may be suboptimal for other languages.
 
1
+ ---
2
+ language:
3
+ - en
4
+ base_model:
5
+ - BAAI/bge-m3
6
+ ---
7
  # GeoReranker
8
 
9
  The GeoReranker model is a critical component in Retrieval-Augmented Generation (RAG) systems, designed to refine the initial retrieval results by reordering candidate documents based on their semantic relevance to the query. Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
 
35
 
36
 
37
  ## Limitations
38
+ GeoReranker is trained on English datasets, and performance may be suboptimal for other languages.