initial commit

.gitattributes

@@ -0,0 +1 @@
+*.onnx filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.venv

README.md

@@ -0,0 +1,66 @@
+---
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+language: en
+license: apache-2.0
+datasets:
+- s2orc
+- flax-sentence-embeddings/stackexchange_xml
+- ms_marco
+- gooaq
+- yahoo_answers_topics
+- code_search_net
+- search_qa
+- eli5
+- snli
+- multi_nli
+- wikihow
+- natural_questions
+- trivia_qa
+- embedding-data/sentence-compression
+- embedding-data/flickr30k-captions
+- embedding-data/altlex
+- embedding-data/simple-wiki
+- embedding-data/QQP
+- embedding-data/SPECTER
+- embedding-data/PAQ_pairs
+- embedding-data/WikiAnswers
+
+---
+
+# ONNX version of sentence-transormers/all-MiniLM-L12-v2
+
+This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. The ONNX version of this model is made for the [Metarank](https://github.com/metarank/metarank) re-ranker
+to do semantic similarity.
+
+Check out the [main Metarank docs](https://docs.metarank.ai) on how to configure it.
+
+TLDR:
+```yaml
+- type: field_match
+  name: title_query_match
+  rankingField: ranking.query
+  itemField: item.title
+  distance: cos 
+  method:
+    type: bert 
+    model: metarank/all-MiniLM-L12-v2
+```
+
+## Building the model
+
+```shell
+$> pip install -r requirements.txt
+$> python convert.py
+
+============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
+verbose: False, log level: Level.ERROR
+======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================
+
+```
+
+## License
+
+Apache 2.0

convert.py

@@ -0,0 +1,11 @@
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L12-v2")
+model.eval()
+
+sample = torch.randint(low=0, high=1, size=(1,128))
+input = (sample, sample, sample)
+
+torch.onnx.export(model, input, 'pytorch_model.onnx', export_params=True)
+

pytorch_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a504d31e57702a74fecf5c2d7df67fa9fcb5635baa2cd335ac74bc2cbdefcbdd
+size 133597269

requirements.txt

@@ -0,0 +1,4 @@
+sentence-transformers==2.2.2
+torch==2.0.0
+onnx==1.13.1
+huggingface_hub==0.13.3