initial commit

.gitattributes

@@ -0,0 +1,3 @@
+*.onnx filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+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 intfloat/multilingual-e5-small
+
+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: bi-encoder 
+    model: metarank/multilingual-e5-small
+```
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

pytorch_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa845c27760e06e9a686b9d8b5d440eae4b6612cd09e5b522b716d3941f77ff
+size 470268533

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b44a9d7b51c3c62626640cda0e2c2f70fdacdc25bbbd68038369d14ebdf4c39
+size 17082730

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}