Add ONNX export for optimized inference

config.json

@@ -1,10 +1,12 @@
 {
+  "_attn_implementation_autoset": true,
   "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "export_model_type": "transformer",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -18,7 +20,6 @@
   "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
   "transformers_version": "4.48.1",
   "type_vocab_size": 2,
   "use_cache": true,

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc15f481426f52523e5695cb7df292a455aed1038d318b5b73672e0dcff3b14
+size 90447733

tokenizer.json

@@ -2,12 +2,14 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
-    "strategy": "BatchLongest",
+    "strategy": {
+      "Fixed": 128
+    },
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

tokenizer_config.json

@@ -48,7 +48,7 @@
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_length": 128,
-  "model_max_length": 256,
+  "model_max_length": 512,
   "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",