johngiorgi commited on
Commit
929b685
1 Parent(s): 8804d85

Add instructions on using with SentenceTransformers

Browse files
Files changed (1) hide show
  1. README.md +24 -1
README.md CHANGED
@@ -12,10 +12,33 @@ The model is intended to be used as a universal sentence encoder, similar to [Go
12
 
13
  Please see [our repo](https://github.com/JohnGiorgi/DeCLUTR) for full details. A simple example is shown below.
14
 
 
 
15
  ```python
16
- import torch
17
  from scipy.spatial.distance import cosine
 
 
 
 
 
 
 
 
 
 
18
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  from transformers import AutoModel, AutoTokenizer
20
 
21
  # Load the model
 
12
 
13
  Please see [our repo](https://github.com/JohnGiorgi/DeCLUTR) for full details. A simple example is shown below.
14
 
15
+ ##### With SentenceTransformers
16
+
17
  ```python
 
18
  from scipy.spatial.distance import cosine
19
+ from sentence_transformers import SentenceTransformer
20
+
21
+ # Load the model
22
+ model = SentenceTransformer("johngiorgi/declutr-small")
23
+
24
+ # Prepare some text to embed
25
+ texts = [
26
+ "A smiling costumed woman is holding an umbrella.",
27
+ "A happy woman in a fairy costume holds an umbrella.",
28
+ ]
29
 
30
+ # Embed the text
31
+ embeddings = model.encode(texts)
32
+
33
+ # Compute a semantic similarity via the cosine distance
34
+ semantic_sim = 1 - cosine(embeddings[0], embeddings[1])
35
+ ```
36
+
37
+ ##### With 🤗 Transformers
38
+
39
+ ```python
40
+ import torch
41
+ from scipy.spatial.distance import cosine
42
  from transformers import AutoModel, AutoTokenizer
43
 
44
  # Load the model