Add new SentenceTransformer model with an onnx backend

1_Pooling/config.json

@@ -5,5 +5,6 @@
   "pooling_mode_max_tokens": false,
   "pooling_mode_mean_sqrt_len_tokens": false,
   "pooling_mode_weightedmean_tokens": false,
-  "pooling_mode_lasttoken": false
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
 }

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "output/train_bi-encoder-mnrl-vinai-phobert-base-v2-margin_3.0-2023-08-27_23-13-25/",
   "architectures": [
     "RobertaModel"
   ],
@@ -21,7 +20,7 @@
   "position_embedding_type": "absolute",
   "tokenizer_class": "PhobertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.52.4",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 64001

config_sentence_transformers.json

@@ -1,7 +1,10 @@
 {
   "__version__": {
-    "sentence_transformers": "2.2.2",
-    "transformers": "4.32.0",
-    "pytorch": "2.0.0+cu117"
-  }
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
 }

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d5be0d0fcbcc27e598d3242b002779df390b563bab968aafade1925fa167cc
+size 537974349

special_tokens_map.json

@@ -1,9 +1,51 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "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": false,
+    "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

@@ -45,8 +45,9 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 256,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "PhobertTokenizer",