Add new SentenceTransformer model.

.gitattributes

@@ -7,3 +7,7 @@
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+flax_model.msgpack filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/af/41/af41d20e942d508261a0f61e30e82d75e8a92740cb691a0d11f0a8025e49e4d4 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/94/12/9412b8f2b54e1aa00593a9b9f0cf0f8c127ff3ec155462d93290594d26a51c28 filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

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

README.md

@@ -1,9 +1,42 @@
-# Sentence Embeddings Models trained on Paraphrases
-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)
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+---
 
-## Usage (HuggingFace Models Repository)
+# sentence-transformers/stsb-roberta-large
+
+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.
+
+
+
+## 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/stsb-roberta-large')
+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
@@ -13,55 +46,54 @@ 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)
-    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
-    return sum_embeddings / sum_mask
-
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
 
 
-#Sentences we want sentence embeddings for
-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.']
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
 
-#Load AutoModel from huggingface model repository
-tokenizer = AutoTokenizer.from_pretrained("model_name")
-model = AutoModel.from_pretrained("model_name")
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/stsb-roberta-large')
+model = AutoModel.from_pretrained('sentence-transformers/stsb-roberta-large')
 
-#Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt')
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
 
-#Compute token embeddings
+# 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('model_name')
-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)
 ```
 
 
+
+## 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/stsb-roberta-large)
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': True}) with Transformer model: RobertaModel 
+  (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})
+)
+```
+
 ## 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

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "old_models/stsb-roberta-large/0_Transformer",
   "architectures": [
     "RobertaModel"
   ],
@@ -19,6 +19,8 @@
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
   "type_vocab_size": 1,
+  "use_cache": true,
   "vocab_size": 50265
 }

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"
+  }
+]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af41d20e942d508261a0f61e30e82d75e8a92740cb691a0d11f0a8025e49e4d4
-size 1421534091
+oid sha256:d96e3630c418e7477298d942ac680e708a8c2f4f2aabc38dad9803b098c7546f
+size 1421590449

tokenizer_config.json

@@ -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"}
+{"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"}