Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,7 @@ tags:
|
|
8 |
- transformers
|
9 |
datasets:
|
10 |
- tarudesu/ViHealthQA
|
|
|
11 |
---
|
12 |
|
13 |
# nampham1106/bkcare-embedding
|
@@ -18,19 +19,24 @@ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentence
|
|
18 |
|
19 |
## Usage (Sentence-Transformers)
|
20 |
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
pip install -U sentence-transformers
|
25 |
-
|
|
|
|
|
|
|
26 |
|
27 |
Then you can use the model like this:
|
28 |
|
29 |
```python
|
30 |
from sentence_transformers import SentenceTransformer
|
31 |
-
|
|
|
32 |
|
33 |
model = SentenceTransformer('nampham1106/bkcare-embedding')
|
|
|
34 |
embeddings = model.encode(sentences)
|
35 |
print(embeddings)
|
36 |
```
|
@@ -43,7 +49,7 @@ Without [sentence-transformers](https://www.SBERT.net), you can use the model li
|
|
43 |
```python
|
44 |
from transformers import AutoTokenizer, AutoModel
|
45 |
import torch
|
46 |
-
|
47 |
|
48 |
#Mean Pooling - Take attention mask into account for correct averaging
|
49 |
def mean_pooling(model_output, attention_mask):
|
@@ -53,12 +59,13 @@ def mean_pooling(model_output, attention_mask):
|
|
53 |
|
54 |
|
55 |
# Sentences we want sentence embeddings for
|
56 |
-
sentences = [
|
57 |
|
58 |
# Load model from HuggingFace Hub
|
59 |
tokenizer = AutoTokenizer.from_pretrained('nampham1106/bkcare-embedding')
|
60 |
model = AutoModel.from_pretrained('nampham1106/bkcare-embedding')
|
61 |
|
|
|
62 |
# Tokenize sentences
|
63 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
64 |
|
|
|
8 |
- transformers
|
9 |
datasets:
|
10 |
- tarudesu/ViHealthQA
|
11 |
+
license: mit
|
12 |
---
|
13 |
|
14 |
# nampham1106/bkcare-embedding
|
|
|
19 |
|
20 |
## Usage (Sentence-Transformers)
|
21 |
|
22 |
+
### Installation <a name="install1"></a>
|
23 |
+
- Install `sentence-transformers`:
|
24 |
+
|
25 |
+
- `pip install -U sentence-transformers`
|
26 |
+
|
27 |
+
- Install `pyvi` to word segment:
|
28 |
+
- `pip install pyvi`
|
29 |
+
### Example usage <a name="usage1"></a>
|
30 |
|
31 |
Then you can use the model like this:
|
32 |
|
33 |
```python
|
34 |
from sentence_transformers import SentenceTransformer
|
35 |
+
from pyvi.ViTokenizer import tokenize
|
36 |
+
sentences = ["Đang chích ngừa viêm gan B có chích ngừa Covid-19 được không?", "Nếu anh / chị đang tiêm ngừa vaccine phòng_bệnh viêm_gan B , anh / chị vẫn có_thể tiêm phòng vaccine phòng Covid-19 , tuy_nhiên vaccine Covid-19 phải được tiêm cách trước và sau mũi vaccine viêm gan B tối_thiểu là 14 ngày ."]
|
37 |
|
38 |
model = SentenceTransformer('nampham1106/bkcare-embedding')
|
39 |
+
sentences = [tokenize(sentence) for sentence in sentences]
|
40 |
embeddings = model.encode(sentences)
|
41 |
print(embeddings)
|
42 |
```
|
|
|
49 |
```python
|
50 |
from transformers import AutoTokenizer, AutoModel
|
51 |
import torch
|
52 |
+
from pyvi.ViTokenizer import tokenize
|
53 |
|
54 |
#Mean Pooling - Take attention mask into account for correct averaging
|
55 |
def mean_pooling(model_output, attention_mask):
|
|
|
59 |
|
60 |
|
61 |
# Sentences we want sentence embeddings for
|
62 |
+
sentences = ["Đang chích ngừa viêm gan B có chích ngừa Covid-19 được không?", "Nếu anh / chị đang tiêm ngừa vaccine phòng_bệnh viêm_gan B , anh / chị vẫn có_thể tiêm phòng vaccine phòng Covid-19 , tuy_nhiên vaccine Covid-19 phải được tiêm cách trước và sau mũi vaccine viêm gan B tối_thiểu là 14 ngày ."]
|
63 |
|
64 |
# Load model from HuggingFace Hub
|
65 |
tokenizer = AutoTokenizer.from_pretrained('nampham1106/bkcare-embedding')
|
66 |
model = AutoModel.from_pretrained('nampham1106/bkcare-embedding')
|
67 |
|
68 |
+
sentences = [tokenize(sentence) for sentence in sentences]
|
69 |
# Tokenize sentences
|
70 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
71 |
|