Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ 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/whitespacetokenizer_config.json 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 sha256:281048beb0a574a237d6b3fc18677ef4b990603045dd79850e9cd0b3df24697d
+size 1115529722

0_WordEmbeddings/whitespacetokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a977819b8f3b192cfaa734d41fc22263405f72964980c328578aefe1ac512544
+size 12971116

0_WordEmbeddings/wordembedding_config.json

@@ -0,0 +1,5 @@
+{
+  "tokenizer_class": "sentence_transformers.models.tokenizer.WhitespaceTokenizer.WhitespaceTokenizer",
+  "update_embeddings": false,
+  "max_seq_length": 1000000
+}

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 300,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,69 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+language:
+- pt
+---
+
+# mteb-pt/average_pt_nilc_word2vec_skip_s300
+
+This is an adaptation of pre-trained Portuguese Word2Vec Word Embeddings to a [sentence-transformers](https://www.SBERT.net) model.  
+
+The original pre-trained word embeddings can be found at: [http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc](http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc).  
+
+This model maps sentences & paragraphs to a 300 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('mteb-pt/average_pt_nilc_word2vec_skip_s300')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Evaluation Results
+
+For an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: [mteb-pt/leaderboard](https://huggingface.co/spaces/mteb-pt/leaderboard)
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): WordEmbeddings(
+    (emb_layer): Embedding(929607, 300)
+  )
+  (1): Pooling({'word_embedding_dimension': 300, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Citing & Authors
+
+```bibtex
+@inproceedings{hartmann2017portuguese,
+    title  = {Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks},
+    author = {Hartmann, Nathan S and
+              Fonseca, Erick R and
+              Shulby, Christopher D and
+              Treviso, Marcos V and
+              Rodrigues, J{'{e}}ssica S and
+              Alu{'{\i}}sio, Sandra Maria},
+    year = {2017},
+    publisher = {SBC},
+    booktitle = {Brazilian Symposium in Information and Human Language Technology - STIL},
+    url = {https://sol.sbc.org.br/index.php/stil/article/view/4008}
+}
+```

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.6.1",
+    "transformers": "4.39.0.dev0",
+    "pytorch": "2.2.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

modules.json

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