thenlper commited on
Commit
ccf2953
1 Parent(s): bb4efcf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -3,6 +3,7 @@ tags:
3
  - mteb
4
  - sentence-similarity
5
  - sentence-transformers
 
6
  model-index:
7
  - name: gte-large
8
  results:
@@ -2637,7 +2638,7 @@ We compared the performance of the GTE models with other popular text embedding
2637
 
2638
  Code example
2639
 
2640
- ```
2641
  import torch.nn.functional as F
2642
  from torch import Tensor
2643
  from transformers import AutoTokenizer, AutoModel
@@ -2669,6 +2670,18 @@ scores = (embeddings[:1] @ embeddings[1:].T) * 100
2669
  print(scores.tolist())
2670
  ```
2671
 
 
 
 
 
 
 
 
 
 
 
 
 
2672
  ### Limitation
2673
 
2674
  This model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens.
 
3
  - mteb
4
  - sentence-similarity
5
  - sentence-transformers
6
+ - Sentence Transformers
7
  model-index:
8
  - name: gte-large
9
  results:
 
2638
 
2639
  Code example
2640
 
2641
+ ```python
2642
  import torch.nn.functional as F
2643
  from torch import Tensor
2644
  from transformers import AutoTokenizer, AutoModel
 
2670
  print(scores.tolist())
2671
  ```
2672
 
2673
+ Use with sentence-transformers:
2674
+ ```python
2675
+ from sentence_transformers import SentenceTransformer
2676
+ from sentence_transformers.util import cos_sim
2677
+
2678
+ sentences = ['That is a happy person', 'That is a very happy person']
2679
+
2680
+ model = SentenceTransformer('thenlper/gte-large')
2681
+ embeddings = model.encode(sentences)
2682
+ print(cos_sim(embeddings[0], embeddings[1]))
2683
+ ```
2684
+
2685
  ### Limitation
2686
 
2687
  This model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens.