binhcode25
commited on
Commit
•
fa475c1
1
Parent(s):
9344179
Upload using huggingface_hub
Browse files- README.md +61 -0
- config.json +23 -0
- model.onnx +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
# onnx-models/multi-qa-distilbert-cos-v1-onnx
|
12 |
+
|
13 |
+
This is the ONNX-ported version of the [sentence-transformers/multi-qa-distilbert-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-distilbert-cos-v1) for generating text embeddings.
|
14 |
+
|
15 |
+
## Model details
|
16 |
+
- Embedding dimension: 768
|
17 |
+
- Max sequence length: 512
|
18 |
+
- File size on disk: 0.25 GB
|
19 |
+
- Modules incorporated in the onnx: Transformer, Pooling, Normalize
|
20 |
+
|
21 |
+
<!--- Describe your model here -->
|
22 |
+
|
23 |
+
## Usage
|
24 |
+
|
25 |
+
Using this model becomes easy when you have [light-embed](https://pypi.org/project/light-embed/) installed:
|
26 |
+
|
27 |
+
```
|
28 |
+
pip install -U light-embed
|
29 |
+
```
|
30 |
+
|
31 |
+
Then you can use the model by specifying the *original model name* like this:
|
32 |
+
|
33 |
+
```python
|
34 |
+
from light_embed import TextEmbedding
|
35 |
+
sentences = [
|
36 |
+
"This is an example sentence",
|
37 |
+
"Each sentence is converted"
|
38 |
+
]
|
39 |
+
|
40 |
+
model = TextEmbedding('sentence-transformers/multi-qa-distilbert-cos-v1')
|
41 |
+
embeddings = model.encode(sentences)
|
42 |
+
print(embeddings)
|
43 |
+
```
|
44 |
+
|
45 |
+
or by specifying the *onnx model name* like this:
|
46 |
+
|
47 |
+
```python
|
48 |
+
from light_embed import TextEmbedding
|
49 |
+
sentences = [
|
50 |
+
"This is an example sentence",
|
51 |
+
"Each sentence is converted"
|
52 |
+
]
|
53 |
+
|
54 |
+
model = TextEmbedding('onnx-models/multi-qa-distilbert-cos-v1-onnx')
|
55 |
+
embeddings = model.encode(sentences)
|
56 |
+
print(embeddings)
|
57 |
+
```
|
58 |
+
|
59 |
+
## Citing & Authors
|
60 |
+
|
61 |
+
Binh Nguyen / [email protected]
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/multi-qa-distilbert-cos-v1",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"transformers_version": "4.8.2",
|
22 |
+
"vocab_size": 30522
|
23 |
+
}
|
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9344de63973186620ea4742d822eff676f87d9f3731298e60cdd22d7993a609
|
3 |
+
size 265618449
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"max_length": 250,
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_to_multiple_of": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"pad_token_type_id": 0,
|
53 |
+
"padding_side": "right",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "DistilBertTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "[UNK]"
|
62 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|