Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,40 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
language:
|
4 |
+
- zh
|
5 |
---
|
6 |
+
|
7 |
+
|
8 |
+
|
9 |
+
| Model | STS-B | ATEC | LCQMC | Avg. |
|
10 |
+
|:-----------------------:|:-----:|:-----:|:-----:|:-----:|
|
11 |
+
| [hellonlp/promcse-roberta-base-zh(sup)](https://huggingface.co/hellonlp/promcse-roberta-base-zh) | 83.89| -| -| -|
|
12 |
+
|
13 |
+
|
14 |
+
|
15 |
+
|
16 |
+
To use the tool, first install the `promcse` package from [PyPI](https://pypi.org/project/promcse/)
|
17 |
+
```bash
|
18 |
+
pip install promcse
|
19 |
+
```
|
20 |
+
|
21 |
+
After installing the package, you can load our model by two lines of code
|
22 |
+
```python
|
23 |
+
from promcse import PromCSE
|
24 |
+
model = PromCSE("hellonlp/promcse-roberta-base-zh", "cls", 10)
|
25 |
+
|
26 |
+
```
|
27 |
+
|
28 |
+
Then you can use our model for **encoding sentences into embeddings**
|
29 |
+
```python
|
30 |
+
embeddings = model.encode("武汉是一个美丽的城市。")
|
31 |
+
```
|
32 |
+
|
33 |
+
**Compute the cosine similarities** between two groups of sentences
|
34 |
+
```python
|
35 |
+
sentences_a = ['武汉是一个美丽的城市。']
|
36 |
+
sentences_b = ['北京是一个美丽的城市。', '北京是一个美丽的城市。']
|
37 |
+
similarities = model.similarity(sentences_a, sentences_b)
|
38 |
+
```
|
39 |
+
|
40 |
+
|