Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06fb85120e40adf0ab188c4f0cc7684f702cb2023532947d1b85f325b0a3645c
+size 2363431

README.md

@@ -1,42 +1,77 @@
 ---
+pipeline_tag: sentence-similarity
 tags:
 - sentence-transformers
 - feature-extraction
+- sentence-similarity
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
 ---
-# LaBSE Pytorch Version 
-This is a pytorch port of the tensorflow version of [LaBSE](https://tfhub.dev/google/LaBSE/1).
 
-To get the sentence embeddings, you can  use the following code:
-```python
-from transformers import AutoTokenizer, AutoModel
+# sentence-transformers/LaBSE
 
-tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/LaBSE")
-model = AutoModel.from_pretrained("sentence-transformers/LaBSE")
+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.
 
-sentences = ["Hello World", "Hallo Welt"]
 
-encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=64, return_tensors='pt')
 
-with torch.no_grad():
-    model_output = model(**encoded_input)
+## Usage (Sentence-Transformers)
 
-embeddings = model_output.pooler_output
-embeddings = torch.nn.functional.normalize(embeddings)
-print(embeddings)
+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:
 
-When you have [sentence-transformers](https://www.sbert.net/) installed, you can use the model like this:
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["Hello World", "Hallo Welt"]
+sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('LaBSE')
+model = SentenceTransformer('sentence-transformers/LaBSE')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
 
-## Reference:
-Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Narveen Ari, Wei Wang. [Language-agnostic BERT Sentence Embedding](https://arxiv.org/abs/2007.01852). July 2020
 
-License: [https://tfhub.dev/google/LaBSE/1](https://tfhub.dev/google/LaBSE/1)
+
+## 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/LaBSE)
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+  (3): Normalize()
+)
+```
+
+## 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",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "http://arxiv.org/abs/1908.10084",
+}
+```

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "old_models/LaBSE/0_Transformer",
   "architectures": [
     "BertModel"
   ],
@@ -21,6 +22,9 @@
   "pooler_num_fc_layers": 3,
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
   "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 501153
 }

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 +1,26 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d3f6a70294b88e8f7d8920f312de9a56fa412c67188f05ca4ebe7a9de17e56
-size 1888175414
+oid sha256:c9e7daf739f87c2168a6d1baffdae5782eceb03eb6de61950284a925234c6865
+size 1883785969

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "model_max_length": 512}
+{"do_lower_case": false, "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, "special_tokens_map_file": "labse-pytorch/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "old_models/LaBSE/0_Transformer", "do_basic_tokenize": true, "never_split": null}