nreimers
commited on
Commit
•
77001b1
1
Parent(s):
a71956f
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +7 -0
- README.md +60 -44
- config.json +2 -1
- config_sentence_transformers.json +7 -0
- modules.json +14 -0
- pytorch_model.bin +2 -2
- sentence_bert_config.json +2 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
7 |
+
}
|
README.md
CHANGED
@@ -1,8 +1,22 @@
|
|
1 |
-
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
4 |
-
## Usage (Sentence Transformers)
|
5 |
-
Using this model becomes more convenient when you have [sentence-transformers](https://github.com/UKPLab/sentence-transformers) installed:
|
6 |
```
|
7 |
pip install -U sentence-transformers
|
8 |
```
|
@@ -10,24 +24,19 @@ pip install -U sentence-transformers
|
|
10 |
Then you can use the model like this:
|
11 |
|
12 |
```python
|
13 |
-
from sentence_transformers import SentenceTransformer
|
14 |
-
|
15 |
-
|
16 |
-
query_embedding = model.encode('How many people live in London?')
|
17 |
-
|
18 |
-
#The passages are encoded as [ [title1, text1], [title2, text2], ...]
|
19 |
-
passage_embedding = model.encode([['London', 'London has 9,787,426 inhabitants at the 2011 census.']])
|
20 |
|
21 |
-
|
|
|
|
|
22 |
```
|
23 |
|
24 |
-
Note: For the passage, we have to encode the Wikipedia article title together with a text paragraph from that article.
|
25 |
|
26 |
|
|
|
|
|
27 |
|
28 |
-
## Usage (HuggingFace Models Repository)
|
29 |
-
|
30 |
-
You can use the model directly from the model repository to compute sentence embeddings:
|
31 |
```python
|
32 |
from transformers import AutoTokenizer, AutoModel
|
33 |
import torch
|
@@ -37,47 +46,54 @@ import torch
|
|
37 |
def mean_pooling(model_output, attention_mask):
|
38 |
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
39 |
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
40 |
-
|
41 |
-
|
42 |
-
return sum_embeddings / sum_mask
|
43 |
|
|
|
|
|
44 |
|
|
|
|
|
|
|
45 |
|
46 |
-
#
|
47 |
-
|
48 |
|
49 |
-
#
|
50 |
-
|
51 |
-
|
52 |
|
53 |
-
#
|
54 |
-
|
55 |
-
model = AutoModel.from_pretrained("model_name")
|
56 |
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
encoded_input = tokenizer(titles, sentences, padding=True, truncation=True, return_tensors='pt')
|
61 |
-
else:
|
62 |
-
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
63 |
|
64 |
-
#Compute query embeddings
|
65 |
-
with torch.no_grad():
|
66 |
-
model_output = model(**encoded_input)
|
67 |
|
68 |
-
#Perform pooling. In this case, mean pooling
|
69 |
-
return mean_pooling(model_output, encoded_input['attention_mask'])
|
70 |
|
71 |
-
|
72 |
-
|
73 |
-
|
|
|
|
|
74 |
|
75 |
-
|
76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
## Citing & Authors
|
|
|
|
|
|
|
79 |
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
|
80 |
-
```
|
81 |
@inproceedings{reimers-2019-sentence-bert,
|
82 |
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
83 |
author = "Reimers, Nils and Gurevych, Iryna",
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: sentence-similarity
|
3 |
+
tags:
|
4 |
+
- sentence-transformers
|
5 |
+
- feature-extraction
|
6 |
+
- sentence-similarity
|
7 |
+
- transformers
|
8 |
+
---
|
9 |
+
|
10 |
+
# sentence-transformers/nq-distilbert-base-v1
|
11 |
+
|
12 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
13 |
+
|
14 |
+
|
15 |
+
|
16 |
+
## Usage (Sentence-Transformers)
|
17 |
+
|
18 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
19 |
|
|
|
|
|
20 |
```
|
21 |
pip install -U sentence-transformers
|
22 |
```
|
|
|
24 |
Then you can use the model like this:
|
25 |
|
26 |
```python
|
27 |
+
from sentence_transformers import SentenceTransformer
|
28 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
|
|
|
|
|
|
|
|
|
|
29 |
|
30 |
+
model = SentenceTransformer('sentence-transformers/nq-distilbert-base-v1')
|
31 |
+
embeddings = model.encode(sentences)
|
32 |
+
print(embeddings)
|
33 |
```
|
34 |
|
|
|
35 |
|
36 |
|
37 |
+
## Usage (HuggingFace Transformers)
|
38 |
+
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
|
39 |
|
|
|
|
|
|
|
40 |
```python
|
41 |
from transformers import AutoTokenizer, AutoModel
|
42 |
import torch
|
|
|
46 |
def mean_pooling(model_output, attention_mask):
|
47 |
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
48 |
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
49 |
+
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
50 |
+
|
|
|
51 |
|
52 |
+
# Sentences we want sentence embeddings for
|
53 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
54 |
|
55 |
+
# Load model from HuggingFace Hub
|
56 |
+
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/nq-distilbert-base-v1')
|
57 |
+
model = AutoModel.from_pretrained('sentence-transformers/nq-distilbert-base-v1')
|
58 |
|
59 |
+
# Tokenize sentences
|
60 |
+
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
61 |
|
62 |
+
# Compute token embeddings
|
63 |
+
with torch.no_grad():
|
64 |
+
model_output = model(**encoded_input)
|
65 |
|
66 |
+
# Perform pooling. In this case, max pooling.
|
67 |
+
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
|
|
68 |
|
69 |
+
print("Sentence embeddings:")
|
70 |
+
print(sentence_embeddings)
|
71 |
+
```
|
|
|
|
|
|
|
72 |
|
|
|
|
|
|
|
73 |
|
|
|
|
|
74 |
|
75 |
+
## Evaluation Results
|
76 |
+
|
77 |
+
|
78 |
+
|
79 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/nq-distilbert-base-v1)
|
80 |
|
81 |
+
|
82 |
+
|
83 |
+
## Full Model Architecture
|
84 |
+
```
|
85 |
+
SentenceTransformer(
|
86 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
87 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
88 |
+
)
|
89 |
+
```
|
90 |
|
91 |
## Citing & Authors
|
92 |
+
|
93 |
+
This model was trained by [sentence-transformers](https://www.sbert.net/).
|
94 |
+
|
95 |
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
|
96 |
+
```bibtex
|
97 |
@inproceedings{reimers-2019-sentence-bert,
|
98 |
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
99 |
author = "Reimers, Nils and Gurevych, Iryna",
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertModel"
|
@@ -18,5 +18,6 @@
|
|
18 |
"seq_classif_dropout": 0.2,
|
19 |
"sinusoidal_pos_embds": false,
|
20 |
"tie_weights_": true,
|
|
|
21 |
"vocab_size": 30522
|
22 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "old_models/nq-distilbert-base-v1/0_Transformer",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertModel"
|
|
|
18 |
"seq_classif_dropout": 0.2,
|
19 |
"sinusoidal_pos_embds": false,
|
20 |
"tie_weights_": true,
|
21 |
+
"transformers_version": "4.7.0",
|
22 |
"vocab_size": 30522
|
23 |
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
}
|
7 |
+
}
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
pytorch_model.bin
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 sha256:23c0560e56779aa0a6de87b189c591bf719a52482b4dab4a9ca5eedf59f9cb4c
|
3 |
+
size 265486777
|
sentence_bert_config.json
CHANGED
@@ -1,3 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length": 512
|
|
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "/
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "old_models/nq-distilbert-base-v1/0_Transformer", "special_tokens_map_file": "/home/ukp-reimers/msmarco/output/distilbert-base-uncased-mined_hard_neg-mean-pooling-no_identifier-epoch10-batchsize75-NTXentLossTriplet-2021-01-08_17-47-51/0_Transformer/special_tokens_map.json", "do_basic_tokenize": true, "never_split": null}
|