binhcode25
commited on
Commit
•
b0fffd1
1
Parent(s):
a6919a4
Add new SentenceTransformer model.
Browse files- README.md +46 -0
- config.json +1 -1
- model.onnx +2 -2
- model_description.json +6 -0
- model_descriptions.json +5 -0
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: light-embed
|
3 |
+
pipeline_tag: sentence-similarity
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
|
9 |
+
---
|
10 |
+
|
11 |
+
# baai-bge-base-en-v1
|
12 |
+
|
13 |
+
This is the ONNX version of the Sentence Transformers model BAAI/bge-base-en-v1.5 for sentence embedding, optimized for speed and lightweight performance. By utilizing onnxruntime and tokenizers instead of heavier libraries like sentence-transformers and transformers, this version ensures a smaller library size and faster execution. Below are the details of the model:
|
14 |
+
- Base model: BAAI/bge-base-en-v1.5
|
15 |
+
- Embedding dimension: 768
|
16 |
+
- Max sequence length: 512
|
17 |
+
- File size on disk: 0.41 GB
|
18 |
+
- Pooling incorporated: Yes
|
19 |
+
|
20 |
+
This ONNX model consists all components in the original sentence transformer model:
|
21 |
+
Transformer, Pooling, Normalize
|
22 |
+
|
23 |
+
<!--- Describe your model here -->
|
24 |
+
|
25 |
+
## Usage (LightEmbed)
|
26 |
+
|
27 |
+
Using this model becomes easy when you have [LightEmbed](https://pypi.org/project/light-embed/) installed:
|
28 |
+
|
29 |
+
```
|
30 |
+
pip install -U light-embed
|
31 |
+
```
|
32 |
+
|
33 |
+
Then you can use the model like this:
|
34 |
+
|
35 |
+
```python
|
36 |
+
from light_embed import TextEmbedding
|
37 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
38 |
+
|
39 |
+
model = TextEmbedding('BAAI/bge-base-en-v1.5')
|
40 |
+
embeddings = model.encode(sentences)
|
41 |
+
print(embeddings)
|
42 |
+
```
|
43 |
+
|
44 |
+
## Citing & Authors
|
45 |
+
|
46 |
+
Binh Nguyen / binhcode25@gmail.com
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "BAAI/bge-base-en-v1.5",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
model.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c118e62068f138542aa1060a6439a2662c7828a2cadba8fb7d220052159ea0
|
3 |
+
size 435917673
|
model_description.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model": "BAAI/bge-base-en-v1.5",
|
3 |
+
"embedding_dim": 768,
|
4 |
+
"max_seq_length": 512,
|
5 |
+
"model_file_size (GB)": 0.41
|
6 |
+
}
|
model_descriptions.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model": "BAAI/bge-base-en-v1.5",
|
3 |
+
"embedding_dim": 768,
|
4 |
+
"max_seq_length": 512
|
5 |
+
}
|