Add new SentenceTransformer model.

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+0_WordEmbeddings/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

0_WordEmbeddings/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5b33893b640864c7368a024463acf602d81ebddd34fae7d9a2f083bbd58868
+size 42848043

0_WordEmbeddings/tokenize_fn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a30b1330f70b9cbd264085c41abbf6e6622654a5afd27c2cb5f91b8140d63e0
+size 69

0_WordEmbeddings/wordembedding_config.json

@@ -0,0 +1,5 @@
+{
+  "tokenizer_class": "mlutil.sentence_transformers_utils.CustomTokenizer",
+  "update_embeddings": false,
+  "max_seq_length": 1000000
+}

2_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 200,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,60 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# lambdaofgod/document-titles-nbow-nbow-mnrl
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 200 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## 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('lambdaofgod/document-titles-nbow-nbow-mnrl')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=lambdaofgod/document-titles-nbow-nbow-mnrl)
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): WordEmbeddings(
+    (emb_layer): Embedding(53559, 200)
+  )
+  (1): WordWeights(
+    (emb_layer): Embedding(53559, 1)
+  )
+  (2): Pooling({'word_embedding_dimension': 200, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.20.0",
+    "pytorch": "1.10.0+cu111"
+  }
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "0_WordEmbeddings",
+    "type": "sentence_transformers.models.WordEmbeddings"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_WordWeights",
+    "type": "sentence_transformers.models.WordWeights"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]