Onnx models compatible with sentence_transformers

config.json

@@ -1,33 +1,31 @@
 {
-    "_name_or_path": "./bert-base-uncased-msmarco",
-    "adapters": {
-      "adapters": {},
-      "config_map": {},
-      "fusion_config_map": {},
-      "fusions": {}
-    },
-    "architectures": [
-      "BertForMaskedLM"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "classifier_dropout": null,
-    "gradient_checkpointing": false,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "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",
-    "torch_dtype": "float32",
-    "transformers_version": "4.26.1",
-    "type_vocab_size": 2,
-    "use_cache": true,
-    "vocab_size": 30522
-  }
-  
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -1,9 +1,9 @@
 {
   "model_type": "SparseEncoder",
   "__version__": {
-    "sentence_transformers": "5.0.0",
-    "transformers": "4.50.3",
-    "pytorch": "2.6.0+cu124"
+    "sentence_transformers": "5.1.1",
+    "transformers": "4.53.3",
+    "pytorch": "2.8.0+cu128"
   },
   "prompts": {
     "query": "",

onnx/model.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e4c016d7aa78e4d87de177508e1b87d3c8e289788ce2fd35ce753614e96425a
-size 532126852

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "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

@@ -1,16 +1,65 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 128,
   "model_max_length": 512,
-  "name_or_path": "Luyu/co-condenser-marco",
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": "/bos/tmp0/luyug/outputs/condenser/models/l2-s6-km-L128-e8-lr1e-4-b256/special_tokens_map.json",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }