Upload 17 files

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/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a548639f4e10e8b96be6a4846f0932ca2d011d491b37489a6b4751a3c096e49d
+size 132

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4af843f3f778124777c11604c9e22c6afdca8c27764a44961099e981cf6355d
+size 132

README.md

@@ -0,0 +1,168 @@
+---
+language:
+- multilingual
+- af
+- sq
+- am
+- ar
+- hy
+- as
+- az
+- eu
+- be
+- bn
+- bs
+- bg
+- my
+- ca
+- ceb
+- zh
+- co
+- hr
+- cs
+- da
+- nl
+- en
+- eo
+- et
+- fi
+- fr
+- fy
+- gl
+- ka
+- de
+- el
+- gu
+- ht
+- ha
+- haw
+- he
+- hi
+- hmn
+- hu
+- is
+- ig
+- id
+- ga
+- it
+- ja
+- jv
+- kn
+- kk
+- km
+- rw
+- ko
+- ku
+- ky
+- lo
+- la
+- lv
+- lt
+- lb
+- mk
+- mg
+- ms
+- ml
+- mt
+- mi
+- mr
+- mn
+- ne
+- no
+- ny
+- or
+- fa
+- pl
+- pt
+- pa
+- ro
+- ru
+- sm
+- gd
+- sr
+- st
+- sn
+- si
+- sk
+- sl
+- so
+- es
+- su
+- sw
+- sv
+- tl
+- tg
+- ta
+- tt
+- te
+- th
+- bo
+- tr
+- tk
+- ug
+- uk
+- ur
+- uz
+- vi
+- cy
+- wo
+- xh
+- yi
+- yo
+- zu
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+library_name: sentence-transformers
+license: apache-2.0
+---
+
+# LaBSE
+This is a port of the [LaBSE](https://tfhub.dev/google/LaBSE/1) model to PyTorch. It can be used to map 109 languages to a shared vector space.
+
+
+## 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/LaBSE')
+embeddings = model.encode(sentences)
+print(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/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
+
+Have a look at [LaBSE](https://tfhub.dev/google/LaBSE/1) for the respective publication that describes LaBSE.
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "old_models/LaBSE/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "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"
+  }
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211fcbb6fed2aedfa31e7da2ecd7ac485ac8010de6e18afbd8c00f722b18c8cc
+size 135

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6566b39f08255d6abd32052675a6534fc20f5c262ce06e2ab5862dbd01cf7b7d
+size 135

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6ff92c0dc1e0e18a7abf27a78921b7cd1a8c51373b44970e718efc81aada64
+size 135

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0ebd757dea4709bb5d69d66ed94e6e46f5275d67ac5f04d791b7854106a885
+size 135

tokenizer_config.json

@@ -0,0 +1 @@
+{"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": "special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "old_models/LaBSE/0_Transformer", "do_basic_tokenize": true, "never_split": null}