Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

README.md

@@ -1,20 +1,47 @@
 ---
-language: en
+pipeline_tag: sentence-similarity
 tags:
-- exbert
+- sentence-transformers
-license: apache-2.0
+- feature-extraction
-datasets:
+- sentence-similarity
-- snli
+- transformers
-- multi_nli
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
 ---
 
-# BERT base model (uncased) for Sentence Embeddings
+# sentence-transformers/bert-base-nli-mean-tokens
-This is the `bert-base-nli-mean-tokens` model from the [sentence-transformers](https://github.com/UKPLab/sentence-transformers)-repository. The sentence-transformers repository allows to train and use Transformer models for generating sentence and text embeddings. 
-The model is described in  the paper  [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084)
 
-## Usage (HuggingFace Models Repository)
+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.
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('sentence-transformers/bert-base-nli-mean-tokens')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+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.
 
-You can use the model directly from the model repository to compute sentence embeddings:
 ```python
 from transformers import AutoTokenizer, AutoModel
 import torch
@@ -24,55 +51,54 @@ import torch
 def mean_pooling(model_output, attention_mask):
     token_embeddings = model_output[0] #First element of model_output contains all token embeddings
     input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
-    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
-    return sum_embeddings / sum_mask
 
 
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
 
-#Sentences we want sentence embeddings for
+# Load model from HuggingFace Hub
-sentences = ['This framework generates embeddings for each input sentence',
+tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-nli-mean-tokens')
-             'Sentences are passed as a list of string.',
+model = AutoModel.from_pretrained('sentence-transformers/bert-base-nli-mean-tokens')
-             'The quick brown fox jumps over the lazy dog.']
 
-#Load AutoModel from huggingface model repository
+# Tokenize sentences
-tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/bert-base-nli-mean-tokens")
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
-model = AutoModel.from_pretrained("sentence-transformers/bert-base-nli-mean-tokens")
 
-#Tokenize sentences
+# Compute token embeddings
-encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt')
-
-#Compute token embeddings
 with torch.no_grad():
     model_output = model(**encoded_input)
 
-#Perform pooling. In this case, mean pooling
+# Perform pooling. In this case, max pooling.
 sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-```
-
-## Usage (Sentence-Transformers)
-Using this model becomes more convenient when you have [sentence-transformers](https://github.com/UKPLab/sentence-transformers) installed:
-```
-pip install -U sentence-transformers
-```
-
-Then you can use the model like this:
-```python
-from sentence_transformers import SentenceTransformer
-model = SentenceTransformer('bert-base-nli-mean-tokens')
-sentences = ['This framework generates embeddings for each input sentence',
-    'Sentences are passed as a list of string.', 
-    'The quick brown fox jumps over the lazy dog.']
-sentence_embeddings = model.encode(sentences)
 
 print("Sentence embeddings:")
 print(sentence_embeddings)
 ```
 
 
-## Citing & Authors
+
-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):
+## Evaluation Results
+
+
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-nli-mean-tokens)
+
+
+
+## Full Model Architecture
 ```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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})
+)
+```
+
+## Citing & Authors
+
+This model was trained by [sentence-transformers](https://www.sbert.net/). 
+        
+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):
+```bibtex 
 @inproceedings{reimers-2019-sentence-bert,
     title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
     author = "Reimers, Nils and Gurevych, Iryna",

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "old_models/bert-base-nli-mean-tokens/0_BERT",
   "architectures": [
     "BertModel"
   ],
@@ -15,6 +16,9 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
   "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -1,3 +1,4 @@
 {
-  "max_seq_length": 128
+  "max_seq_length": 128,
+  "do_lower_case": false
 }

tokenizer_config.json

@@ -0,0 +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, "special_tokens_map_file": "old_models/bert-base-nli-mean-tokens/0_BERT/special_tokens_map.json", "name_or_path": "old_models/bert-base-nli-mean-tokens/0_BERT", "do_basic_tokenize": true, "never_split": null}