nreimers commited on
Commit
2113e9d
1 Parent(s): 6c6988e
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ tags:
13
 
14
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search.
15
 
16
- This model was converted from the Tensorflow model [gtr-base-1](https://tfhub.dev/google/gtr/gtr-base/1) to PyTorch. When using this model, have a look at the publication: [Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899)
17
 
18
  The model uses only the encoder from a T5-base model. The weights are stored in FP16.
19
 
13
 
14
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search.
15
 
16
+ This model was converted from the Tensorflow model [gtr-base-1](https://tfhub.dev/google/gtr/gtr-base/1) to PyTorch. When using this model, have a look at the publication: [Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899). The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results.
17
 
18
  The model uses only the encoder from a T5-base model. The weights are stored in FP16.
19