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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+library_name: light-embed
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# sbert-paraphrase-multilingual-mpnet-base-v2-onnx
+
+This is the ONNX version of the Sentence Transformers model sentence-transformers/paraphrase-multilingual-mpnet-base-v2 for sentence embedding, optimized for speed and lightweight performance. By utilizing onnxruntime and tokenizers instead of heavier libraries like sentence-transformers and transformers, this version ensures a smaller library size and faster execution. Below are the details of the model:
+- Base model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+- Embedding dimension: 768
+- Max sequence length: 128
+- File size on disk:  1.03 GB
+
+This ONNX model consists all components in the original sentence transformer model:
+Transformer, Pooling
+
+<!--- Describe your model here -->
+
+## Usage (LightEmbed)
+
+Using this model becomes easy when you have [LightEmbed](https://www.light-embed.net) installed:
+
+```
+pip install -U light-embed
+```
+
+Then you can use the model like this:
+
+```python
+from light_embed import TextEmbedding
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = TextEmbedding('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Citing & Authors
+
+Binh Nguyen / binhcode25@gmail.com

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "old_models/paraphrase-multilingual-mpnet-base-v2/0_Transformer",
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
   "architectures": [
     "XLMRobertaModel"
   ],
@@ -24,4 +24,4 @@
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002
-}
+}

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d861af7f0cd24a08328481404d330f2cb112258d14a358affba649572d9c509
-size 1112421935
+oid sha256:acb89c010c252fa5b50750ccd41d454dec43cb9f8c2c9c6b743930509d89d41b
+size 1110169923

model_description.json

@@ -0,0 +1,6 @@
+{
+  "base_model": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+  "embedding_dim": 768,
+  "max_seq_length": 128,
+  "model_file_size (GB)": 1.03
+}

modules.json

@@ -2,13 +2,11 @@
   {
     "idx": 0,
     "name": "0",
-    "path": "",
     "type": "sentence_transformers.models.Transformer"
   },
   {
     "idx": 1,
     "name": "1",
-    "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
   }
 ]

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -1 +1,51 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1 +1,61 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/paraphrase-multilingual-mpnet-base-v2/0_Transformer"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}