mixed-nlp commited on
Commit
fef70ba
1 Parent(s): 723f7bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -2618,7 +2618,9 @@ This is our [2DMSE](https://arxiv.org/abs/2402.14776) sentence embedding model.
2618
 
2619
  ## Quickstart
2620
 
2621
- ### sentence-transformers
 
 
2622
 
2623
  Currently, the best way to use our models is with the most recent version of sentence-transformers.
2624
 
@@ -2656,7 +2658,7 @@ similarities = cos_sim(embeddings[0, :new_embedding_size], embeddings[1, :new_em
2656
  print('similarities:', similarities)
2657
  ```
2658
 
2659
- ### angle-emb
2660
 
2661
  You can also use the lastest `angle-emb` for inference, as follows:
2662
 
@@ -2686,6 +2688,7 @@ similarities = cos_sim(embeddings[0], embeddings[1:])
2686
  print('similarities:', similarities)
2687
  ```
2688
 
2689
- ### Using API
 
2690
  You’ll be able to use the models through our API as well. The API is coming soon and will have some exciting features. Stay tuned!
2691
 
 
2618
 
2619
  ## Quickstart
2620
 
2621
+ Here, we provide several ways to produce sentence embeddings with adaptive layers and embedding sizes. **For this version, it is recommended to set adaptive layers from 20 to 24.**
2622
+
2623
+ ### 1. sentence-transformers
2624
 
2625
  Currently, the best way to use our models is with the most recent version of sentence-transformers.
2626
 
 
2658
  print('similarities:', similarities)
2659
  ```
2660
 
2661
+ ### 2. angle-emb
2662
 
2663
  You can also use the lastest `angle-emb` for inference, as follows:
2664
 
 
2688
  print('similarities:', similarities)
2689
  ```
2690
 
2691
+ ### 3. Using API
2692
+
2693
  You’ll be able to use the models through our API as well. The API is coming soon and will have some exciting features. Stay tuned!
2694