Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,29 @@ colorFrom: yellow
|
|
5 |
colorTo: yellow
|
6 |
sdk: static
|
7 |
pinned: false
|
|
|
8 |
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
colorTo: yellow
|
6 |
sdk: static
|
7 |
pinned: false
|
8 |
+
license: apache-2.0
|
9 |
---
|
10 |
|
11 |
+
Hierarchy Transformers (HiTs) are capable of interpreting and encoding hierarchies explicitly.
|
12 |
+
|
13 |
+
The relevant code in [HierarchyTransformers](https://github.com/KRR-Oxford/HierarchyTransformers) extends from [Sentence-Transformers](https://huggingface.co/sentence-transformers).
|
14 |
+
|
15 |
+
Example usage:
|
16 |
+
|
17 |
+
```python
|
18 |
+
from hierarchy_transformers import HierarchyTransformer
|
19 |
+
from hierarchy_transformers.utils import get_torch_device
|
20 |
+
|
21 |
+
# set up the device (use cpu if no gpu found)
|
22 |
+
gpu_id = 0
|
23 |
+
device = get_torch_device(gpu_id)
|
24 |
+
|
25 |
+
# load the model
|
26 |
+
model = HierarchyTransformer.load_pretrained('Hierarchy-Transformers/HiT-MiniLM-L12-WordNet')
|
27 |
+
|
28 |
+
# entity names to be encoded.
|
29 |
+
entity_names = ["computer", "personal computer", "laptop"]
|
30 |
+
|
31 |
+
# get the entity embeddings
|
32 |
+
entity_embeddings = model.encode(entity_names)
|
33 |
+
```
|