nreimers commited on
Commit
5a39ea1
1 Parent(s): 2db5260

Add new SentenceTransformer model.

Browse files
.gitattributes CHANGED
@@ -7,3 +7,7 @@
7
  *.ot filter=lfs diff=lfs merge=lfs -text
8
  *.onnx filter=lfs diff=lfs merge=lfs -text
9
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
7
  *.ot filter=lfs diff=lfs merge=lfs -text
8
  *.onnx filter=lfs diff=lfs merge=lfs -text
9
  *.msgpack filter=lfs diff=lfs merge=lfs -text
10
+ flax_model.msgpack filter=lfs diff=lfs merge=lfs -text
11
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
12
+ .git/lfs/objects/af/41/af41d20e942d508261a0f61e30e82d75e8a92740cb691a0d11f0a8025e49e4d4 filter=lfs diff=lfs merge=lfs -text
13
+ .git/lfs/objects/94/12/9412b8f2b54e1aa00593a9b9f0cf0f8c127ff3ec155462d93290594d26a51c28 filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
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
@@ -1,9 +1,42 @@
1
- # Sentence Embeddings Models trained on Paraphrases
2
- This model is from the [sentence-transformers](https://github.com/UKPLab/sentence-transformers)-repository. It was trained on SNLI + MultiNLI and on STS benchmark dataset. Further details on SBERT can be found in the paper: [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084)
 
 
 
 
 
 
3
 
4
- ## Usage (HuggingFace Models Repository)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
- You can use the model directly from the model repository to compute sentence embeddings:
7
  ```python
8
  from transformers import AutoTokenizer, AutoModel
9
  import torch
@@ -13,55 +46,54 @@ import torch
13
  def mean_pooling(model_output, attention_mask):
14
  token_embeddings = model_output[0] #First element of model_output contains all token embeddings
15
  input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
16
- sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
17
- sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
18
- return sum_embeddings / sum_mask
19
-
20
 
21
 
22
- #Sentences we want sentence embeddings for
23
- sentences = ['This framework generates embeddings for each input sentence',
24
- 'Sentences are passed as a list of string.',
25
- 'The quick brown fox jumps over the lazy dog.']
26
 
27
- #Load AutoModel from huggingface model repository
28
- tokenizer = AutoTokenizer.from_pretrained("model_name")
29
- model = AutoModel.from_pretrained("model_name")
30
 
31
- #Tokenize sentences
32
- encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt')
33
 
34
- #Compute token embeddings
35
  with torch.no_grad():
36
  model_output = model(**encoded_input)
37
 
38
- #Perform pooling. In this case, mean pooling
39
  sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
40
- ```
41
-
42
- ## Usage (Sentence-Transformers)
43
- Using this model becomes more convenient when you have [sentence-transformers](https://github.com/UKPLab/sentence-transformers) installed:
44
- ```
45
- pip install -U sentence-transformers
46
- ```
47
-
48
- Then you can use the model like this:
49
- ```python
50
- from sentence_transformers import SentenceTransformer
51
- model = SentenceTransformer('model_name')
52
- sentences = ['This framework generates embeddings for each input sentence',
53
- 'Sentences are passed as a list of string.',
54
- 'The quick brown fox jumps over the lazy dog.']
55
- sentence_embeddings = model.encode(sentences)
56
 
57
  print("Sentence embeddings:")
58
  print(sentence_embeddings)
59
  ```
60
 
61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  ## Citing & Authors
 
 
 
63
  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):
64
- ```
65
  @inproceedings{reimers-2019-sentence-bert,
66
  title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
67
  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/stsb-roberta-large
11
+
12
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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
+ ```
23
+
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/stsb-roberta-large')
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/stsb-roberta-large')
57
+ model = AutoModel.from_pretrained('sentence-transformers/stsb-roberta-large')
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/stsb-roberta-large)
80
+
81
+
82
+
83
+ ## Full Model Architecture
84
+ ```
85
+ SentenceTransformer(
86
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': True}) with Transformer model: RobertaModel
87
+ (1): Pooling({'word_embedding_dimension': 1024, '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": "roberta-large",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
@@ -19,6 +19,8 @@
19
  "num_hidden_layers": 24,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
 
22
  "type_vocab_size": 1,
 
23
  "vocab_size": 50265
24
  }
 
1
  {
2
+ "_name_or_path": "old_models/stsb-roberta-large/0_Transformer",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
 
19
  "num_hidden_layers": 24,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
+ "transformers_version": "4.7.0",
23
  "type_vocab_size": 1,
24
+ "use_cache": true,
25
  "vocab_size": 50265
26
  }
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:af41d20e942d508261a0f61e30e82d75e8a92740cb691a0d11f0a8025e49e4d4
3
- size 1421534091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96e3630c418e7477298d942ac680e708a8c2f4f2aabc38dad9803b098c7546f
3
+ size 1421590449
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "roberta-large"}
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "old_models/stsb-roberta-large/0_Transformer", "special_tokens_map_file": "old_models/stsb-roberta-large/0_Transformer/special_tokens_map.json"}